© 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. 10-RES-JB
    11. 20449
    Prev
    Next
    INDEX
    Explanations

    summaries or descriptions of various content, such as highlights, excerpts, analyses, and breakdowns

    oai_token-act-pair · gpt-3.5-turbo

    highlighted summaries or excerpts from various reports or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.76
    ndra
    -0.71
    advertising
    -0.70
     Traps
    -0.69
    anes
    -0.67
    minecraft
    -0.64
     Limit
    -0.63
    duc
    -0.61
    uca
    -0.60
     Wheels
    -0.60
    POSITIVE LOGITS
     excerpts
    1.54
     excerpt
    1.33
     transcript
    1.16
     extracts
    1.14
     snippets
    1.12
    cerpt
    1.10
    ographical
    1.04
     quotations
    1.03
     transcription
    1.02
     chronological
    1.00
    Activations Density 0.160%

    No Known Activations