© 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. 11250
    Prev
    Next
    INDEX
    Explanations

    references to recent events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to events that occurred within the last year

    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
    lees
    -0.68
     Logged
    -0.65
     Related
    -0.61
    olla
    -0.61
    ,,,,
    -0.60
    hement
    -0.57
    rentices
    -0.57
     Soldiers
    -0.56
    onto
    -0.55
    quartered
    -0.55
    POSITIVE LOGITS
     year
    1.22
     week
    1.16
     month
    1.09
     weekend
    1.07
     night
    0.99
     summer
    0.97
     ditch
    0.93
     rites
    0.93
    year
    0.91
     season
    0.87
    Activations Density 0.041%

    No Known Activations