© 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. 32287
    Prev
    Next
    INDEX
    Explanations

    action verbs describing the act of adding things

    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
    60
    +0.05
    0.6%
    274
    +0.04
    0.5%
    642
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.05
    0.15
    362
    +0.04
    0.11
    636
    +0.04
    0.07
    Negative Logits
    fare
    -0.34
    LAB
    -0.29
    creen
    -0.28
    Fram
    -0.28
    DAQ
    -0.28
     Gram
    -0.28
     Distribut
    -0.27
    ograms
    -0.27
     guiActiveUnfocused
    -0.27
    é¾įå¥ij士
    -0.26
    POSITIVE LOGITS
    endum
    0.47
    ictions
    0.37
    apses
    0.35
    enda
    0.34
    apse
    0.33
    ulate
    0.33
    icts
    0.32
    eston
    0.32
     insult
    0.32
    ressing
    0.32
    Activations Density 5.496%

    No Known Activations