© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40839
    Prev
    Next
    INDEX
    Explanations

    references to people's names

    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
    706
    +0.14
    0.6%
    389
    +0.13
    0.6%
    7
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.14
    0.09
    685
    +0.13
    0.01
    224
    +0.13
    0.09
    Negative Logits
     eminent
    -0.63
    matically
    -0.62
     caucuses
    -0.61
    regor
    -0.61
     pound
    -0.61
     Camel
    -0.60
     Wilhelm
    -0.59
     Clarkson
    -0.59
     wallets
    -0.59
    oslav
    -0.58
    POSITIVE LOGITS
    cue
    1.41
    istance
    1.39
    idency
    1.22
    pring
    1.19
    erve
    1.19
    olutions
    1.17
    cale
    1.17
    urrection
    1.16
    olver
    1.13
    idents
    1.10
    Activations Density 7.725%

    No Known Activations