© 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. 7-RES-JB
    11. 13430
    Prev
    Next
    INDEX
    Explanations

    mentions of famous or well-known things or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "famous" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    THER
    -0.80
    ilation
    -0.78
    ©¶æ
    -0.76
    heed
    -0.76
    idia
    -0.71
    plet
    -0.70
    appointed
    -0.69
    iland
    -0.69
    sure
    -0.68
    asse
    -0.66
    POSITIVE LOGITS
     landmarks
    0.88
     quote
    0.82
     quotes
    0.80
     Circus
    0.75
     quotations
    0.74
     quotation
    0.72
     example
    0.70
     surname
    0.69
     bearer
    0.67
     Quote
    0.66
    Activations Density 0.033%

    No Known Activations