© 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. 45787
    Prev
    Next
    INDEX
    Explanations

    phrases related to the iTunes platform and music artists

    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
    288
    +0.12
    0.5%
    651
    +0.11
    0.5%
    491
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.19
    326
    +0.11
    0.18
    651
    +0.10
    0.10
    Negative Logits
    wart
    -0.77
    minded
    -0.76
    rely
    -0.75
    agh
    -0.73
    emate
    -0.71
    fighting
    -0.71
    stal
    -0.70
    racted
    -0.70
    unal
    -0.70
    pled
    -0.68
    POSITIVE LOGITS
     Store
    1.07
     Stores
    0.97
     iTunes
    0.93
    Store
    0.90
    CRIP
    0.89
     Springs
    0.82
    pring
    0.80
     Movies
    0.77
    Leaks
    0.77
     Moj
    0.77
    Activations Density 6.052%

    No Known Activations