© 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. 13751
    Prev
    Next
    INDEX
    Explanations

    phrases relating to repetition or identical instances

    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
    162
    +0.12
    0.5%
    213
    +0.11
    0.4%
    672
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.12
    0.06
    393
    +0.11
    0.20
    279
    +0.11
    0.10
    Negative Logits
    *=-
    -0.89
    emi
    -0.87
     Provided
    -0.83
    ohyd
    -0.82
    acus
    -0.81
    âĵĺ
    -0.79
    ases
    -0.76
    ç«
    -0.75
    alf
    -0.75
     Bei
    -0.75
    POSITIVE LOGITS
     thing
    1.14
     exact
    1.09
     amount
    1.01
     vein
    0.94
     kind
    0.91
     kinds
    0.87
    rity
    0.81
     spot
    0.81
    iating
    0.81
    worldly
    0.80
    Activations Density 8.963%

    No Known Activations