© 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. 9479
    Prev
    Next
    INDEX
    Explanations

    words related to providing evidence or confirmation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal or substantive discussions

    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
    ged
    -0.83
    nesday
    -0.82
    bors
    -0.80
    enhagen
    -0.78
    sonian
    -0.77
    gerald
    -0.76
    fle
    -0.74
    keley
    -0.73
    lem
    -0.72
    gets
    -0.72
    POSITIVE LOGITS
     substant
    0.85
    ively
    0.77
    igr
    0.75
    ŃĶ
    0.75
    ially
    0.71
    iations
    0.71
    iate
    0.70
    ĸļ
    0.69
    afort
    0.68
    ËĪ
    0.66
    Activations Density 0.023%

    No Known Activations