© 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 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. 9-RES-JB
    11. 4642
    Prev
    Next
    INDEX
    Explanations

    dates and specific moments in time

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation marks in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usable
    -0.78
     contribution
    -0.75
     temperament
    -0.74
     propensity
    -0.73
    oes
    -0.72
    catentry
    -0.72
    untarily
    -0.71
     affili
    -0.71
     committing
    -0.70
     distinguishing
    -0.70
    POSITIVE LOGITS
     Suddenly
    1.32
     Thousands
    1.27
     Dozens
    1.21
     Hundreds
    1.19
     Everyone
    1.13
     Shortly
    1.10
     Yesterday
    1.08
     Ahead
    1.08
     Immediately
    1.08
     Someone
    1.07
    Activations Density 0.511%

    No Known Activations