© 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. 34774
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions for recipes

    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
    +0.32
    1.4%
    640
    +0.24
    1.0%
    481
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.32
    0.34
    160
    +0.24
    0.23
    6
    +0.12
    0.19
    Negative Logits
    itism
    -0.93
     evidenced
    -0.87
     manifests
    -0.77
    fm
    -0.73
    ocrin
    -0.72
     veter
    -0.70
    ¥µ
    -0.69
    arios
    -0.69
     Loren
    -0.67
     experien
    -0.67
    POSITIVE LOGITS
    Ingredients
    1.07
    Optional
    0.97
     Instructions
    0.95
    Instruct
    0.94
    ½
    0.94
    ulsion
    0.94
    Salt
    0.90
    -+-+-+-+
    0.87
    poon
    0.86
    ³³³³
    0.86
    Activations Density 10.868%

    No Known Activations