© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 13432
    Prev
    Next
    INDEX
    Explanations

    words related to political or social tension

    oai_token-act-pair · gpt-3.5-turbo

    references to escalating conflicts or disagreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cise
    -0.79
    icle
    -0.75
    ardi
    -0.70
    icles
    -0.69
    prints
    -0.69
    option
    -0.69
    ãģ®å
    -0.65
    sole
    -0.65
    otto
    -0.65
    glas
    -0.63
    POSITIVE LOGITS
     flared
    0.91
     cooker
    0.87
     tension
    0.87
     tensions
    0.86
    rained
    0.80
     flare
    0.79
     simmer
    0.78
     escal
    0.78
     surrounding
    0.78
     eb
    0.77
    Activations Density 0.043%

    No Known Activations