© 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. 20264
    Prev
    Next
    INDEX
    Explanations

    verbs related to decision-making or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "vote" or related voting terminology

    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
     Henri
    -0.70
    ryu
    -0.65
     coax
    -0.65
     depletion
    -0.63
     conditioning
    -0.62
     phen
    -0.62
     nib
    -0.62
     Huang
    -0.62
     peripheral
    -0.62
     disorders
    -0.61
    POSITIVE LOGITS
     Vote
    4.17
    Vote
    2.80
    vote
    2.04
     Votes
    1.99
     Voters
    1.82
     Voting
    1.80
     vote
    1.64
     Voter
    1.58
     votes
    1.45
    votes
    1.39
    Activations Density 0.012%

    No Known Activations