© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14805
    Prev
    Next
    INDEX
    Explanations

    mentions of activities or items related to solo performances

    oai_token-act-pair · gpt-3.5-turbo

    references to solo performances or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mosp
    -0.81
    nant
    -0.73
    mos
    -0.68
     Hussein
    -0.68
     inacc
    -0.67
    tics
    -0.66
     Authorities
    -0.64
    oras
    -0.63
    ENCY
    -0.61
     Ezekiel
    -0.61
    POSITIVE LOGITS
    iliary
    0.91
     solo
    0.89
    icated
    0.82
    spective
    0.81
     piano
    0.78
    uthor
    0.72
    ized
    0.72
    allo
    0.70
    andowski
    0.70
    ited
    0.68
    Activations Density 0.009%

    No Known Activations