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. 4439
    Prev
    Next
    INDEX
    Explanations

    complex phrases and sentences with multiple hyphens

    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
    314
    +0.11
    0.5%
    616
    +0.10
    0.5%
    664
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.35
    160
    +0.10
    0.29
    102
    +0.10
    0.18
    Negative Logits
     Richards
    -0.68
     Polo
    -0.66
     Swordsman
    -0.65
     Discipline
    -0.63
     Burnett
    -0.62
    ITION
    -0.62
     Brush
    -0.61
     Fallon
    -0.61
     Pell
    -0.59
     Ascension
    -0.59
    POSITIVE LOGITS
    everal
    1.03
    only
    1.00
    ettings
    0.91
    based
    0.91
    inspired
    0.88
    sembly
    0.88
    forward
    0.88
    rights
    0.85
    themed
    0.84
    uper
    0.84
    Activations Density 9.279%

    No Known Activations