© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 17595
    Prev
    Next
    INDEX
    Explanations

    references to political parties and figures, as well as societal issues

    oai_token-act-pair · gpt-3.5-turbo

    references to political parties and their influence on societal issues

    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
     Originally
    -0.72
    raft
    -0.70
    escription
    -0.70
     unusual
    -0.69
     âĨij
    -0.65
    hatt
    -0.65
     initially
    -0.65
     approached
    -0.63
     aback
    -0.63
    atta
    -0.63
    POSITIVE LOGITS
     theirs
    0.93
     civilized
    0.90
     negro
    0.89
     THEIR
    0.89
     idiots
    0.88
     tyranny
    0.87
     patri
    0.87
     ignor
    0.87
     goddamn
    0.84
     trillions
    0.84
    Activations Density 1.601%

    No Known Activations