© 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. 7-RES-JB
    11. 17089
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "voters"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of voters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceFile
    -0.84
    ity
    -0.82
    Else
    -0.76
    uran
    -0.68
     Chef
    -0.68
     Protocol
    -0.67
    cer
    -0.66
     Pace
    -0.64
    kefeller
    -0.64
     Flavoring
    -0.63
    POSITIVE LOGITS
    ndum
    0.90
     turnout
    0.86
    hip
    0.81
     polled
    0.80
     disillusion
    0.76
     beware
    0.76
     voters
    0.75
     disenfranch
    0.74
     tuning
    0.70
     ballots
    0.70
    Activations Density 0.022%

    No Known Activations