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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 13637
    Prev
    Next
    INDEX
    Explanations

    words related to re-election

    oai_token-act-pair · gpt-3.5-turbo

    terms related to electoral processes and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spring
    -0.79
    §
    -0.70
    early
    -0.66
    DEP
    -0.66
    Lens
    -0.66
     Colon
    -0.65
    ijn
    -0.65
    Bio
    -0.65
    tto
    -0.65
    iday
    -0.64
    POSITIVE LOGITS
     rigged
    0.86
     bribe
    0.73
    roc
    0.73
    partisan
    0.72
     rigging
    0.70
     minded
    0.70
     Kremlin
    0.69
    clinton
    0.69
     incompetent
    0.69
     sided
    0.68
    Activations Density 0.008%

    No Known Activations