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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14087
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of explanations or justifications

    oai_token-act-pair · gpt-3.5-turbo

    mention of "reasons" or phrases discussing multiple factors or justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enged
    -0.66
    inis
    -0.64
    iasco
    -0.63
     Observer
    -0.61
    velt
    -0.61
    helps
    -0.60
    oba
    -0.60
    ibaba
    -0.60
    yss
    -0.60
    externalActionCode
    -0.60
    POSITIVE LOGITS
     reasons
    1.07
     unrelated
    0.95
    abl
    0.92
     inexplicable
    0.89
     unexplained
    0.88
     why
    0.82
     unspecified
    0.82
     alone
    0.81
     sake
    0.81
     unknown
    0.81
    Activations Density 0.056%

    No Known Activations