© 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. 9-RES-JB
    6. 1677
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    references to sports figures or events

    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
     periodic
    -0.70
     cessation
    -0.69
     vain
    -0.68
     comet
    -0.67
     ministerial
    -0.66
     pipe
    -0.65
     garden
    -0.65
     carriage
    -0.64
     administration
    -0.64
     minion
    -0.63
    POSITIVE LOGITS
    advertising
    1.51
    Released
    1.11
    Probably
    1.10
    Age
    1.05
    Another
    1.05
    Introduced
    1.01
    Few
    1.01
    Quite
    0.99
    Height
    0.99
    Honestly
    0.98
    Activations Density 0.205%

    No Known Activations