© 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. 7632
    Prev
    Next
    INDEX
    Explanations

    topics related to the extent of something or finding phrases discussing the extent to which certain conditions or situations occur

    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
    195
    +0.16
    0.5%
    183
    +0.16
    0.5%
    642
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.16
    0.03
    724
    +0.16
    0.03
    312
    +0.16
    0.02
    Negative Logits
    tty
    -1.11
    reth
    -1.01
    pton
    -0.98
    asted
    -0.97
    itone
    -0.92
     Bans
    -0.91
    imen
    -0.90
    ween
    -0.89
    cair
    -0.89
    aida
    -0.87
    POSITIVE LOGITS
     extent
    1.37
     practicable
    1.06
    ially
    1.02
    essment
    0.96
    conom
    0.95
    esm
    0.94
    iece
    0.89
    Æ
    0.88
    semb
    0.87
    ional
    0.86
    Activations Density 0.244%

    No Known Activations