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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 40217
    Prev
    Next
    INDEX
    Explanations

    phrases related to music concerts, musical performances, and event organizing

    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%
    257
    +0.10
    0.6%
    749
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    614
    +0.19
    0.04
    270
    +0.10
    0.04
    216
    +0.09
    0.09
    Negative Logits
    lean
    -0.62
     Ruler
    -0.61
    ãĥĥãĥī
    -0.61
     nutshell
    -0.59
    oil
    -0.57
    metics
    -0.57
     implants
    -0.56
    cheat
    -0.54
    hair
    -0.54
    poor
    -0.54
    POSITIVE LOGITS
    goers
    1.16
     attendees
    0.93
     attendance
    0.86
     venue
    0.81
     pav
    0.79
    atorium
    0.77
     concerts
    0.77
     organizers
    0.77
     venues
    0.75
     gatherings
    0.74
    Activations Density 15.433%

    No Known Activations