© 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. 36770
    Prev
    Next
    INDEX
    Explanations

    Mad Max-themed words

    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
    105
    +0.08
    0.5%
    556
    +0.07
    0.4%
    176
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.08
    0.11
    406
    +0.07
    0.10
    299
    +0.06
    0.10
    Negative Logits
    fecture
    -0.50
    lator
    -0.49
    taboola
    -0.49
    emp
    -0.49
    isconsin
    -0.46
     Osc
    -0.46
    Dialogue
    -0.44
    dest
    -0.44
    igslist
    -0.44
     fungi
    -0.43
    POSITIVE LOGITS
    coni
    0.53
     Mania
    0.49
    nas
    0.49
    chief
    0.47
     Brah
    0.45
    oka
    0.45
    Angelo
    0.44
     filibuster
    0.44
     Madness
    0.44
     Krishna
    0.43
    Activations Density 9.655%

    No Known Activations