© 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. 4-RES-JB
    11. 7598
    Prev
    Next
    INDEX
    Explanations

    phrases related to a political campaign

    oai_token-act-pair · gpt-3.5-turbo

    words related to "para" and "ana," likely indicating discussions about specific types of analyses or conditions

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

    No Comments

    Negative Logits
    sburg
    -0.95
    esley
    -0.83
    Ö¼
    -0.81
    hart
    -0.79
    endor
    -0.78
    soever
    -0.77
     Clarkson
    -0.74
    20439
    -0.73
    bies
    -0.72
    bie
    -0.72
    POSITIVE LOGITS
    esthes
    0.94
    esthesia
    0.93
    forming
    0.91
     compr
    0.82
    esthetic
    0.78
     cling
    0.73
     cord
    0.73
     para
    0.72
    odic
    0.72
    ulic
    0.71
    Activations Density 0.016%

    No Known Activations