© 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. 8-RES-JB
    11. 22519
    Prev
    Next
    INDEX
    Explanations

    months

    oai_token-act-pair · gpt-3.5-turbo

    references to specific months, particularly October and November

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Īè
    -0.73
    Lear
    -0.73
    ascript
    -0.71
    cheon
    -0.69
    culosis
    -0.68
    umbai
    -0.68
    ħĭ
    -0.66
    jriwal
    -0.66
    ciplinary
    -0.65
    acted
    -0.65
    POSITIVE LOGITS
    nard
    0.89
    tag
    0.73
    sburg
    0.68
    lene
    0.68
    ne
    0.63
    quist
    0.63
    ibel
    0.62
     Hare
    0.62
    bris
    0.62
    urnal
    0.60
    Activations Density 0.083%

    No Known Activations