© 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. 10-RES-JB
    11. 24035
    Prev
    Next
    INDEX
    Explanations

    words related to events or actions causing significant reactions or impact

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in the text

    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
    REDACTED
    -0.74
     sqor
    -0.67
    antly
    -0.66
    sein
    -0.65
    itely
    -0.65
    untarily
    -0.64
    inately
    -0.64
    orem
    -0.63
    ptin
    -0.63
    onym
    -0.63
    POSITIVE LOGITS
     which
    1.41
     whose
    1.31
     wherein
    1.11
    whose
    1.11
    which
    1.10
     where
    1.08
     whom
    1.05
     whereby
    1.02
     who
    1.00
     particularly
    0.97
    Activations Density 0.335%

    No Known Activations