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. 14210
    Prev
    Next
    INDEX
    Explanations

    information related to updates or changes in a program or project

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant statements or updates regarding events and submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     UNCLASSIFIED
    -0.57
    natureconservancy
    -0.57
    +.
    -0.54
    ++;
    -0.54
     vanquished
    -0.51
    yright
    -0.50
    icable
    -0.50
    !.
    -0.50
    less
    -0.50
    usercontent
    -0.49
    POSITIVE LOGITS
    ventus
    0.47
    Term
    0.46
     Portsmouth
    0.46
    ffer
    0.46
    ridor
    0.45
    Net
    0.45
    itially
    0.45
    assetsadobe
    0.45
    izons
    0.45
    resa
    0.45
    Activations Density 0.393%

    No Known Activations