© 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. 0-RES-JB
    11. 22754
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making and options

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "choice."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scl
    -0.75
    Report
    -0.69
    ews
    -0.68
    iba
    -0.68
    Downloadha
    -0.67
    Ct
    -0.66
    ean
    -0.66
    ibo
    -0.66
    ami
    -0.66
    borough
    -0.62
    POSITIVE LOGITS
     choice
    3.98
    choice
    2.81
     choices
    2.78
     Choice
    2.44
    Choice
    2.22
     CHO
    1.87
     choosing
    1.82
     selection
    1.70
     option
    1.59
     selections
    1.53
    Activations Density 0.015%

    No Known Activations