© 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. 20286
    Prev
    Next
    INDEX
    Explanations

    mentions of famous people, places, events, or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to well-known individuals, entities, or events

    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
    THER
    -0.79
    ilation
    -0.74
    ©¶æ
    -0.73
    CDC
    -0.72
    adra
    -0.71
    atever
    -0.70
    sure
    -0.69
    ylon
    -0.68
    akings
    -0.68
    required
    -0.68
    POSITIVE LOGITS
     landmarks
    0.88
     quote
    0.86
     quotes
    0.80
     Circus
    0.76
     quotations
    0.71
     unsolved
    0.69
     surname
    0.69
     bust
    0.68
     quotation
    0.68
     bearer
    0.68
    Activations Density 0.039%

    No Known Activations