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. 10-RES-JB
    6. 2839
    Prev
    Next
    INDEX
    Explanations

    words related to responsibility or accountability

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    razil
    -0.71
     ->
    -0.61
     -------
    -0.59
     -->
    -0.58
    wcs
    -0.58
     Starts
    -0.57
     ['
    -0.56
    aeda
    -0.56
     Emails
    -0.56
    achusetts
    -0.55
    POSITIVE LOGITS
     downright
    0.83
     Lovecraft
    0.77
     decidedly
    0.77
     frontman
    0.73
     ABV
    0.72
     splend
    0.72
     solitude
    0.70
     indul
    0.70
     Flavoring
    0.70
     wretched
    0.69
    Activations Density 1.394%

    No Known Activations