© 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. 3-RES-JB
    11. 15147
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to "Kittendales" and persons named "Witt"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ü
    -0.79
    xual
    -0.79
     upheaval
    -0.75
    ©¶æ
    -0.73
    Copy
    -0.72
    mith
    -0.71
    cul
    -0.70
     exha
    -0.69
    ħĭ
    -0.68
     unrest
    -0.63
    POSITIVE LOGITS
    sburgh
    1.31
    sburg
    1.12
     Kitt
    1.01
    gerald
    0.88
    matter
    0.85
    endor
    0.85
    elsen
    0.83
    iors
    0.83
    erella
    0.78
    aceous
    0.78
    Activations Density 0.022%

    No Known Activations