© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7077
    Prev
    Next
    INDEX
    Explanations

    numerical figures or statistics related to distribution or allocation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical accounting or measurement within contexts

    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
    beam
    -0.74
    NetMessage
    -0.70
    cel
    -0.69
    feeding
    -0.63
    BOX
    -0.62
     Letter
    -0.62
    ierre
    -0.62
    feld
    -0.61
    reach
    -0.60
     Hubbard
    -0.60
    POSITIVE LOGITS
    ancy
    0.97
    arily
    0.90
    utical
    0.89
    enance
    0.81
    ominated
    0.77
    atives
    0.76
     balances
    0.74
    Credit
    0.73
     GOODMAN
    0.73
    orea
    0.72
    Activations Density 0.020%

    No Known Activations