© 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. 3-RES-JB
    11. 11315
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific location or sports team

    oai_token-act-pair · gpt-3.5-turbo

    references to specific football clubs and players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enrollment
    -0.73
     variance
    -0.69
     Medicaid
    -0.68
     downside
    -0.64
     LCS
    -0.63
    CEPT
    -0.62
     multiplier
    -0.62
    IDENT
    -0.62
    selection
    -0.61
     attribution
    -0.61
    POSITIVE LOGITS
    wich
    1.65
    pton
    1.15
    sten
    1.01
    thal
    0.94
     Brom
    0.93
    shire
    0.92
    ania
    0.92
    aic
    0.90
    ulla
    0.89
    mere
    0.89
    Activations Density 0.004%

    No Known Activations