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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 17342
    Prev
    Next
    INDEX
    Explanations

    statistics about appearances or performances

    oai_token-act-pair · gpt-3.5-turbo

    the term "appearances" used in the context of sports or performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xon
    -0.71
    rals
    -0.70
    yout
    -0.69
    Mos
    -0.69
    anim
    -0.68
    tones
    -0.66
     reaction
    -0.66
    Reviewer
    -0.65
    behavior
    -0.65
     Cruise
    -0.63
    POSITIVE LOGITS
     unbeaten
    0.91
     Ago
    0.85
    nikov
    0.82
     Played
    0.81
    bley
    0.78
     opener
    0.76
     played
    0.70
    liga
    0.69
     strugg
    0.69
    orial
    0.67
    Activations Density 0.080%

    No Known Activations