© 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. 11167
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a high degree of likelihood or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize high certainty or intensity

    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
    izational
    -0.68
    icable
    -0.67
    arial
    -0.63
    istic
    -0.63
    aphael
    -0.60
    asive
    -0.60
     Atmosp
    -0.59
    ANE
    -0.59
    oresc
    -0.59
    ardo
    -0.59
    POSITIVE LOGITS
    itially
    0.93
    successfully
    0.91
    rouse
    0.91
    edly
    0.91
    ially
    0.89
    aneously
    0.88
    necess
    0.88
    ensibly
    0.88
    rely
    0.86
     accurately
    0.86
    Activations Density 0.068%

    No Known Activations