© 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. 14198
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific years or time periods

    oai_token-act-pair · gpt-3.5-turbo

    frequent mentions of the phrase "Every year" and related yearly events or occurrences

    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
    aye
    -0.81
    nered
    -0.75
    arton
    -0.74
    ferred
    -0.69
    rador
    -0.68
    ieg
    -0.66
    eny
    -0.65
    umbn
    -0.64
    bent
    -0.64
    peria
    -0.63
    POSITIVE LOGITS
     brings
    0.97
     thereafter
    0.89
     somebody
    0.77
     publishes
    0.76
     thousands
    0.73
     contributes
    0.73
     someone
    0.73
     evolves
    0.69
     updates
    0.69
     Learns
    0.68
    Activations Density 0.112%

    No Known Activations