© 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. 11865
    Prev
    Next
    INDEX
    Explanations

    numerical ranges or values

    oai_token-act-pair · gpt-3.5-turbo

    duration and frequency descriptors involving "two and a half" or related time expressions

    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
    Demand
    -0.68
    ippi
    -0.65
    CRE
    -0.64
    çķ
    -0.64
    kson
    -0.60
    abis
    -0.59
    WER
    -0.57
    BALL
    -0.56
    furt
    -0.56
    velt
    -0.55
    POSITIVE LOGITS
    half
    1.01
    ixty
    0.87
     half
    0.86
    Half
    0.86
     twentieth
    0.79
    done
    0.78
     Half
    0.76
    undred
    0.76
    circle
    0.75
    ONE
    0.73
    Activations Density 0.054%

    No Known Activations