© 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. 8-RES-JB
    11. 9047
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with characters or fictional beings

    oai_token-act-pair · gpt-3.5-turbo

    character names from popular media and franchises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IENT
    -0.84
    ailability
    -0.80
     petroleum
    -0.76
    arij
    -0.73
     qualitative
    -0.72
    itutional
    -0.70
    iliated
    -0.69
     campuses
    -0.69
     affiliate
    -0.68
     comprehensive
    -0.67
    POSITIVE LOGITS
     Himself
    1.06
     himself
    1.03
    buster
    0.97
     Costume
    0.95
     Kenobi
    0.95
     Statue
    0.94
     statue
    0.93
     Jr
    0.92
    osaurus
    0.89
    zilla
    0.87
    Activations Density 0.387%

    No Known Activations