© 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. 16837
    Prev
    Next
    INDEX
    Explanations

    words indicating negative or controversial situations

    oai_token-act-pair · gpt-3.5-turbo

    interruptions or ellipses in text

    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
    icum
    -0.81
    rir
    -0.73
    rons
    -0.71
    oit
    -0.71
     purse
    -0.70
    wagen
    -0.70
    fen
    -0.70
     bod
    -0.69
    anqu
    -0.68
    terday
    -0.67
    POSITIVE LOGITS
     Written
    1.03
     Appears
    1.01
    BUT
    0.97
     Continued
    0.85
     ...
    0.83
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.83
     WATCHED
    0.81
     âĢİ
    0.80
    Marginal
    0.80
    CBC
    0.78
    Activations Density 0.008%

    No Known Activations