© 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. 39924
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming terms, such as equations, iterations, and code snippets

    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
    +0.20
    1.4%
    326
    +0.08
    0.5%
    143
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.20
    0.17
    283
    +0.08
    0.00
    49
    +0.07
    0.15
    Negative Logits
    stre
    -0.50
    AIDS
    -0.47
     taxp
    -0.46
    Golden
    -0.46
     Leigh
    -0.45
    âĢİ
    -0.44
     Lebanon
    -0.44
    gay
    -0.44
    Gil
    -0.43
     Trailer
    -0.43
    POSITIVE LOGITS
    omorphic
    0.64
     configure
    0.59
     subclass
    0.58
     duplicate
    0.54
     Qt
    0.52
     CONFIG
    0.51
     CLIENT
    0.51
     router
    0.50
     compute
    0.50
     DEBUG
    0.49
    Activations Density 21.434%

    No Known Activations