© 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. 3-RES-JB
    11. 1763
    Prev
    Next
    INDEX
    Explanations

    statistical and research findings

    oai_token-act-pair · gpt-3.5-turbo

    instances of studies reporting findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GBT
    -0.78
    gur
    -0.65
    mediated
    -0.63
    EStreamFrame
    -0.60
     redes
    -0.59
    trip
    -0.59
    Torrent
    -0.59
    UGE
    -0.57
    via
    -0.56
    jet
    -0.54
    POSITIVE LOGITS
    rition
    0.76
    uggest
    0.72
    ournals
    0.69
     findings
    0.68
    =>
    0.66
    acea
    0.64
    ãģ®å
    0.63
    earcher
    0.63
    ãģ®éŃĶ
    0.61
    iveness
    0.59
    Activations Density 0.132%

    No Known Activations