© 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. 3139
    Prev
    Next
    INDEX
    Explanations

    the surnames "Bett", "Kod", and "Dag" with varying degrees of activation

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and references to specific individuals or organizations

    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
    hyde
    -0.89
    atile
    -0.76
    ysis
    -0.74
    okane
    -0.73
    urrection
    -0.72
    yip
    -0.71
    eting
    -0.70
    erd
    -0.68
    ãĤ£
    -0.66
    omsday
    -0.65
    POSITIVE LOGITS
    dll
    0.74
    ANY
    0.73
    Publisher
    0.73
     BDS
    0.69
    Reviewed
    0.66
    Org
    0.65
    elf
    0.65
    taboola
    0.65
    WB
    0.63
    rieved
    0.62
    Activations Density 0.028%

    No Known Activations