© 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 Local
    9. 6-RES_SCL-AJT
    11. 36014
    Prev
    Next
    INDEX
    Explanations

    dates and numerical sequences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    567
    +0.06
    0.5%
    214
    +0.05
    0.4%
    420
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.06
    0.12
    693
    +0.05
    0.09
    145
    +0.05
    0.06
    Negative Logits
    hide
    -0.41
    ighting
    -0.41
    Reviewed
    -0.40
     takedown
    -0.37
    replace
    -0.37
    âĹ¼
    -0.37
     warranted
    -0.36
    olving
    -0.36
     usability
    -0.35
    ħĭ
    -0.35
    POSITIVE LOGITS
     Died
    0.43
     1959
    0.40
     1928
    0.40
     1952
    0.40
     eldest
    0.38
     1966
    0.37
     Converted
    0.37
     1921
    0.37
     1962
    0.37
     1951
    0.37
    Activations Density 11.164%

    No Known Activations