© 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. 3198
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific forms of disasters or intense situations, often metaphorical

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant themes or concepts linked to existential or societal challenges

    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
    alty
    -0.75
    ynes
    -0.75
    idas
    -0.75
    erion
    -0.74
    ername
    -0.72
    untarily
    -0.71
    arily
    -0.70
    fter
    -0.70
    fur
    -0.68
    quarter
    -0.66
    POSITIVE LOGITS
     sorts
    1.08
     proportions
    0.86
     liberalism
    0.84
     civilization
    0.78
     bureaucracy
    0.77
     contradictions
    0.76
     capitalism
    0.75
     emotions
    0.74
     civilisation
    0.73
     lies
    0.72
    Activations Density 0.176%

    No Known Activations