© 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. 1-RES-JB
    11. 3242
    Prev
    Next
    INDEX
    Explanations

    names of characters and locations from a specific fictional series

    oai_token-act-pair · gpt-3.5-turbo

    character names from a specific TV series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itud
    -0.78
    trak
    -0.75
    score
    -0.73
    isconsin
    -0.72
    EPA
    -0.69
    iba
    -0.68
    lli
    -0.66
    itudes
    -0.64
    oard
    -0.63
    izu
    -0.63
    POSITIVE LOGITS
     Lann
    1.60
     Bolton
    1.18
     Stark
    1.12
     Thrones
    1.10
     Wester
    1.08
     Targ
    1.05
     Robb
    0.92
     Archdemon
    0.85
     compr
    0.84
     tyr
    0.82
    Activations Density 0.027%

    No Known Activations