© 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. 0-RES-JB
    11. 22275
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities, such as "Pablo Escobar" or "Boost.Python"

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent figures and references to authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.75
    ecause
    -0.61
     ItemLevel
    -0.58
    onga
    -0.58
    ogun
    -0.58
    olean
    -0.57
    wark
    -0.55
    him
    -0.54
    ruary
    -0.52
    iard
    -0.51
    POSITIVE LOGITS
     antioxid
    0.89
     Seym
    0.80
    natureconservancy
    0.80
    Balt
    0.78
     millenn
    0.77
     tradem
    0.76
    ß
    0.75
    HUD
    0.74
    GoldMagikarp
    0.73
    kefeller
    0.73
    Activations Density 7.492%

    No Known Activations