© 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. 3106
    Prev
    Next
    INDEX
    Explanations

    questioning or expressing concern about something in a critical manner

    oai_token-act-pair · gpt-3.5-turbo

    phrases that question the consideration of others' needs or perspectives

    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
    arm
    -0.74
    Ãį
    -0.72
    Published
    -0.71
    River
    -0.70
    ¯¯¯¯¯¯¯¯
    -0.70
    ells
    -0.69
    Sher
    -0.68
    oppy
    -0.68
    Thompson
    -0.68
    imb
    -0.68
    POSITIVE LOGITS
    ...?
    0.90
    !?
    0.79
     those
    0.75
     protecting
    0.71
    ?!
    0.70
     fairness
    0.69
    !?"
    0.68
     grandchildren
    0.68
    ?
    0.67
    ?:
    0.66
    Activations Density 0.031%

    No Known Activations