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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 39944
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and distribution of items or information

    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
    +0.09
    1.1%
    101
    +0.05
    0.6%
    508
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.09
    0.09
    59
    +0.05
    0.07
    437
    +0.04
    0.06
    Negative Logits
    chest
    -0.32
    te
    -0.28
    thro
    -0.27
    tes
    -0.27
     lodge
    -0.27
    ton
    -0.26
    thal
    -0.26
     Huss
    -0.26
    thing
    -0.26
    hart
    -0.25
    POSITIVE LOGITS
     leaflets
    0.40
     distribute
    0.37
    DAQ
    0.36
     distributing
    0.35
     disperse
    0.33
     pamph
    0.33
     copies
    0.33
     redistributed
    0.32
     distributed
    0.31
     ILCS
    0.30
    Activations Density 10.533%

    No Known Activations