© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12139
    Prev
    Next
    INDEX
    Explanations

    words related to music and musicians, particularly highlighting specific musicians and musical styles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    618
    +0.13
    0.6%
    679
    +0.11
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    618
    +0.13
    0.13
    679
    +0.11
    0.16
    267
    +0.10
    0.10
    Negative Logits
    brance
    -0.73
    abil
    -0.73
    avorite
    -0.70
    ratom
    -0.68
    eros
    -0.68
    ecast
    -0.66
    zens
    -0.65
    ONT
    -0.65
    atever
    -0.64
    ãģı
    -0.64
    POSITIVE LOGITS
     aptly
    0.98
     remarked
    0.90
     commented
    0.87
     eloqu
    0.85
     bluntly
    0.82
     lamented
    0.81
     omin
    0.81
     warns
    0.80
    :"
    0.80
     "[
    0.78
    Activations Density 5.078%

    No Known Activations