Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3689
    Prev
    Next
    INDEX
    Explanations

    words related to ballot initiatives and political campaigns

    oai_token-act-pair · gpt-3.5-turbo

    references to ballot initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kut
    -0.78
    rir
    -0.75
    hered
    -0.73
    PLIED
    -0.73
    ews
    -0.68
    auga
    -0.66
    ĺħ
    -0.66
    elsen
    -0.64
    sei
    -0.64
     tremend
    -0.64
    POSITIVE LOGITS
     ballots
    0.88
    zeb
    0.87
    ination
    0.86
     canv
    0.81
    room
    0.78
    asso
    0.78
    boxes
    0.77
    otle
    0.76
     Compass
    0.75
    eering
    0.75
    Activations Density 0.016%

    No Known Activations