© 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. 22111
    Prev
    Next
    INDEX
    Explanations

    information about reports, studies, documents, and announcements being released or published

    oai_token-act-pair · gpt-3.5-turbo

    references to reports, studies, or data releases

    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
    intend
    -0.66
    jp
    -0.66
    externalActionCode
    -0.65
    arsity
    -0.64
    isma
    -0.64
    Js
    -0.63
    abiding
    -0.61
    enn
    -0.60
    witch
    -0.60
    esides
    -0.60
    POSITIVE LOGITS
     excerpts
    1.09
     statements
    0.99
     an
    0.96
     findings
    0.93
     a
    0.93
     photographs
    0.92
     transcripts
    0.91
     guidelines
    0.89
     snapshots
    0.89
     pictures
    0.86
    Activations Density 0.137%

    No Known Activations