© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 692
    Prev
    Next
    INDEX
    Explanations

    political statements and intentions related to voting

    oai_token-act-pair · gpt-3.5-turbo

    poll results and opinions regarding political choices

    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
     Miracle
    -0.86
     Atlantis
    -0.83
     Maze
    -0.81
     Complex
    -0.76
     Sph
    -0.75
     Beaut
    -0.70
    humans
    -0.70
     Artemis
    -0.69
     Delivery
    -0.68
    ĸļ
    -0.68
    POSITIVE LOGITS
     voted
    1.50
     vote
    1.47
     voting
    1.39
    ecided
    1.33
    ospons
    1.32
    vote
    1.31
    votes
    1.31
     votes
    1.29
     caucus
    1.27
     endorse
    1.24
    Activations Density 0.613%

    No Known Activations