© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16432
    Prev
    Next
    INDEX
    Explanations

    provocative or controversial statements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     circulating
    -0.75
     flooded
    -0.72
     diversion
    -0.71
     auxiliary
    -0.68
     prescribed
    -0.67
     Haj
    -0.66
     Maxwell
    -0.65
     volunt
    -0.65
     floating
    -0.65
     hovering
    -0.65
    POSITIVE LOGITS
    Br
    3.75
    br
    1.73
    BR
    1.64
     Br
    1.62
     Brus
    1.54
    Fr
    1.25
    Bel
    1.25
    Brand
    1.25
    Buff
    1.20
    Bron
    1.19
    Activations Density 0.010%

    No Known Activations