Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 2984
    Prev
    Next
    INDEX
    Explanations

    statements relating to upcoming events or court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that may indicate important features or elements in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grazing
    -0.70
    TPPStreamerBot
    -0.67
    sted
    -0.63
    zx
    -0.63
    wcs
    -0.62
    ``
    -0.62
    bus
    -0.59
    acci
    -0.59
    phia
    -0.58
    romeda
    -0.57
    POSITIVE LOGITS
     Ibid
    0.85
     Unable
    0.73
     Continued
    0.71
     Measures
    0.70
     Various
    0.69
     Shiv
    0.68
     Subjects
    0.68
     Seek
    0.68
     Proced
    0.66
     Stead
    0.66
    Activations Density 0.092%

    No Known Activations