© 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 EvalsExportsAPI 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. 12166
    Prev
    Next
    INDEX
    Explanations

    substitutions being made in code or data

    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
    288
    +0.28
    1.1%
    679
    +0.20
    0.8%
    724
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.25
    724
    +0.20
    0.20
    575
    +0.12
    0.18
    Negative Logits
    resp
    -0.90
    monds
    -0.84
    ãĥ£
    -0.82
    enegger
    -0.81
    avis
    -0.81
    hing
    -0.79
     nutritious
    -0.78
    wn
    -0.78
     nutrit
    -0.75
    overe
    -0.75
    POSITIVE LOGITS
    eering
    1.19
    ary
    1.11
    ISM
    1.07
    ally
    1.07
    ists
    1.06
    ist
    1.03
    ism
    1.02
     thereof
    0.96
    naire
    0.95
    alist
    0.94
    Activations Density 4.674%

    No Known Activations