© 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. 18607
    Prev
    Next
    INDEX
    Explanations

    mentions of professions or specific roles within various organizations

    oai_token-act-pair · gpt-3.5-turbo

    words related to individuals and groups involved in research or oversight roles

    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
    rection
    -0.64
    TO
    -0.59
     corrective
    -0.59
    kun
    -0.58
    worthiness
    -0.58
    Weapon
    -0.57
    Thumbnail
    -0.57
     dominates
    -0.56
     exists
    -0.56
    SOURCE
    -0.55
    POSITIVE LOGITS
    folk
    1.04
     who
    1.01
    hip
    0.93
    hips
    0.88
    paces
    0.88
     ranging
    0.85
     wishing
    0.83
     nationwide
    0.83
    erv
    0.81
     whose
    0.80
    Activations Density 0.335%

    No Known Activations