© 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. 15266
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics and locations, particularly focusing on a specific individual named Shelby

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific politicians and locations in Alabama

    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
    udence
    -0.86
    irements
    -0.82
    ogens
    -0.81
    rug
    -0.79
    alg
    -0.78
    ards
    -0.76
    _-
    -0.75
    oulder
    -0.73
    orical
    -0.72
    lich
    -0.71
    POSITIVE LOGITS
    ville
    0.81
     Bapt
    0.80
     Ala
    0.80
    berry
    0.75
     Shelby
    0.74
     Montgomery
    0.72
     Knox
    0.70
     County
    0.69
     Marble
    0.68
     Township
    0.68
    Activations Density 0.018%

    No Known Activations