© 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. 4-RES-JB
    11. 19606
    Prev
    Next
    INDEX
    Explanations

    phrases containing a mix of numbers, symbols, and words, with an emphasis on investigative or controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of criminal activities or incidents involving violence

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

    No Comments

    Negative Logits
     Weld
    -0.84
     Lumpur
    -0.71
     Ascension
    -0.67
    DERR
    -0.64
     Ripple
    -0.63
     Tradable
    -0.63
     Seym
    -0.62
     payroll
    -0.61
     Kathryn
    -0.61
     Ross
    -0.61
    POSITIVE LOGITS
    recomm
    0.94
    dead
    0.88
    pre
    0.88
    guide
    0.86
    cell
    0.86
    library
    0.85
    cook
    0.85
    cond
    0.85
    trial
    0.84
    sent
    0.84
    Activations Density 0.075%

    No Known Activations