© 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. 8-RES-JB
    11. 23407
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings and government officials

    oai_token-act-pair · gpt-3.5-turbo

    mentions of legal proceedings or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selves
    -0.66
    .–
    -0.65
    ".[
    -0.63
    )--
    -0.61
    Availability
    -0.60
    idae
    -0.59
    ..."
    -0.57
    Have
    -0.56
    peat
    -0.55
     guiActiveUnfocused
    -0.54
    POSITIVE LOGITS
     himself
    0.77
     herself
    0.71
     emailed
    0.70
     aback
    0.64
     tweeted
    0.63
     firsthand
    0.60
     his
    0.60
    itely
    0.60
     unsuccessfully
    0.58
     scathing
    0.58
    Activations Density 1.161%

    No Known Activations