© 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. 1114
    Prev
    Next
    INDEX
    Explanations

    historical events and political information

    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
    739
    +0.18
    0.6%
    160
    +0.17
    0.6%
    218
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    604
    +0.18
    0.08
    739
    +0.17
    0.06
    618
    +0.14
    0.07
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -1.02
    ikuman
    -0.99
    ãĥ¼ãĥĨ
    -0.92
    ient
    -0.91
    ãĥ¼ãĥ³
    -0.89
    âķIJâķIJ
    -0.87
    acon
    -0.86
     corrid
    -0.84
     surrogate
    -0.84
     Tycoon
    -0.84
    POSITIVE LOGITS
    ...]
    1.74
    âĢ¦]
    1.58
    Pg
    1.43
    ?]
    1.28
    src
    1.22
    !]
    1.19
    REDACTED
    1.16
    ](
    1.14
    note
    1.12
    Footnote
    1.11
    Activations Density 0.471%

    No Known Activations