© 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. 18714
    Prev
    Next
    INDEX
    Explanations

    personal choices and preferences related to decision-making

    oai_token-act-pair · gpt-3.5-turbo

    references to personal choices and social identities

    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
    itous
    -0.77
    cial
    -0.74
     Sloan
    -0.73
     Subtle
    -0.71
    vous
    -0.71
    ļéĨĴ
    -0.70
    urry
    -0.68
    conom
    -0.65
    ifference
    -0.64
    yss
    -0.64
    POSITIVE LOGITS
    'd
    0.78
     chose
    0.77
     choose
    0.76
     chooses
    0.74
     chosen
    0.71
     destined
    0.70
     should
    0.70
     avail
    0.69
    'll
    0.69
     selected
    0.69
    Activations Density 0.158%

    No Known Activations