© 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. 9-RES-JB
    11. 18535
    Prev
    Next
    INDEX
    Explanations

    emphasis or attention-grabbing symbols and text patterns

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cephal
    -0.68
    uces
    -0.66
     spir
    -0.66
     rack
    -0.65
    kered
    -0.65
    azing
    -0.62
     srf
    -0.62
    ved
    -0.62
     scattering
    -0.61
     manifold
    -0.61
    POSITIVE LOGITS
    WARNING
    0.98
    THIS
    0.97
    !/
    0.93
     WARNING
    0.86
    UPDATE
    0.86
    Discussion
    0.82
     ***
    0.82
    NOT
    0.80
    EDIT
    0.80
    DOWN
    0.79
    Activations Density 0.046%

    No Known Activations