Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34490
    Prev
    Next
    INDEX
    Explanations

    technical details and terms related to technology and hardware

    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
    +0.19
    1.0%
    393
    +0.15
    0.8%
    640
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.19
    0.25
    608
    +0.15
    0.19
    703
    +0.12
    0.12
    Negative Logits
    hops
    -0.63
     obliged
    -0.56
    fair
    -0.54
    ossibility
    -0.53
    ouf
    -0.53
    hemat
    -0.52
    obook
    -0.51
    kind
    -0.50
    icum
    -0.50
    soft
    -0.49
    POSITIVE LOGITS
     regard
    1.45
     regards
    1.41
     respect
    1.11
    stood
    0.99
    draw
    0.98
    drawn
    0.87
    standing
    0.86
     impunity
    0.81
    holding
    0.76
     tremend
    0.61
    Activations Density 9.803%

    No Known Activations