© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2042
    Prev
    Next
    INDEX
    Explanations

    people's names prefixed with 'Cl' and 'ib', possibly related to names such as 'Clorox', 'Cliburn', and 'Clofen' and 'Alban'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    349
    +0.15
    0.5%
    543
    +0.14
    0.5%
    185
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.15
    0.07
    701
    +0.14
    0.06
    406
    +0.13
    0.06
    Negative Logits
    agara
    -0.92
     goodwill
    -0.91
     latent
    -0.91
    ONSORED
    -0.91
     discriminate
    -0.90
     warr
    -0.89
     tremend
    -0.86
     contemplate
    -0.85
     discrimination
    -0.84
    OTOS
    -0.84
    POSITIVE LOGITS
    nces
    1.09
    veland
    1.09
    ico
    1.09
    nant
    1.03
    odon
    0.98
    nce
    0.97
    rants
    0.96
    leans
    0.96
    istics
    0.95
    aud
    0.95
    Activations Density 1.470%

    No Known Activations