© 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. 1-RES-JB
    11. 24094
    Prev
    Next
    INDEX
    Explanations

    words related to location names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or titles, particularly related to "aton" and "Eaton."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patent
    -0.75
    PE
    -0.72
     Operation
    -0.69
     Journalists
    -0.68
    Drug
    -0.67
     pus
    -0.64
    behind
    -0.63
     Ethics
    -0.63
    Ey
    -0.62
     incumbent
    -0.62
    POSITIVE LOGITS
    aton
    1.64
    hesda
    1.11
    emouth
    1.11
    alyst
    1.01
    throp
    0.95
    onite
    0.94
    arius
    0.94
    idian
    0.92
    otle
    0.92
    umerable
    0.91
    Activations Density 0.006%

    No Known Activations