© 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. 35865
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and interactions

    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
    447
    +0.17
    1.1%
    566
    +0.12
    0.8%
    296
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.17
    0.27
    354
    +0.12
    0.18
    718
    +0.07
    0.19
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.49
     Tsuk
    -0.48
    ãĥĥ
    -0.48
    nels
    -0.46
    iencies
    -0.46
     Dimension
    -0.45
    loe
    -0.45
    rex
    -0.45
     Sigma
    -0.44
    stellar
    -0.43
    POSITIVE LOGITS
     ever
    0.79
    ever
    0.66
     EVER
    0.57
    'd
    0.55
    'll
    0.53
     wish
    0.52
     slightest
    0.51
     heard
    0.50
     happiest
    0.50
     encount
    0.49
    Activations Density 14.171%

    No Known Activations