© 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. 10-RES-JB
    11. 18538
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a high level of extremity or intensity in actions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate extreme actions or statements, often expressed as "went so far as to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urses
    -0.70
    kes
    -0.69
    urse
    -0.68
    aught
    -0.66
    itu
    -0.66
    bed
    -0.65
    odor
    -0.63
    unct
    -0.62
     cov
    -0.62
    glers
    -0.61
    POSITIVE LOGITS
    WARD
    0.91
     overboard
    0.86
    irtual
    0.83
     lengths
    0.73
     beyond
    0.69
     sidx
    0.68
     towards
    0.67
     abroad
    0.66
    atform
    0.66
     backwards
    0.66
    Activations Density 0.062%

    No Known Activations