© 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
    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. 4975
    Prev
    Next
    INDEX
    Explanations

    French words and phrases

    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
    375
    +0.02
    0.6%
    690
    +0.02
    0.5%
    224
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.02
    0.32
    640
    +0.02
    0.28
    142
    +0.02
    0.13
    Negative Logits
    anthrop
    -0.15
    FACE
    -0.14
    atom
    -0.12
    cale
    -0.12
    hem
    -0.12
    hemer
    -0.12
    print
    -0.11
    xtap
    -0.11
    phas
    -0.11
    older
    -0.11
    POSITIVE LOGITS
    iers
    0.13
     pots
    0.12
    ills
    0.11
     torches
    0.11
     mL
    0.11
     indo
    0.11
    upt
    0.11
    acles
    0.11
     srf
    0.11
     inval
    0.11
    Activations Density 11.804%

    No Known Activations