© 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. 2-RES-JB
    11. 9301
    Prev
    Next
    INDEX
    Explanations

    ISO country codes capitalized

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Toronto

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scl
    -0.85
    ãĤ¦
    -0.83
    hard
    -0.75
    ãĤ±
    -0.73
     Doe
    -0.73
    holder
    -0.72
    ãĥ©ãĥ³
    -0.72
    dates
    -0.70
    hardt
    -0.70
    els
    -0.67
    POSITIVE LOGITS
    TOR
    1.22
    onto
    0.97
    MENT
    0.86
     earthqu
    0.78
    oshenko
    0.77
     TOR
    0.76
     rall
    0.75
    ON
    0.73
    bably
    0.71
     inhibition
    0.70
    Activations Density 0.003%

    No Known Activations