© 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. 16111
    Prev
    Next
    INDEX
    Explanations

    common articles like "a" or "an"

    oai_token-act-pair · gpt-3.5-turbo

    articles and quantifiers preceding nouns

    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
    bis
    -0.74
    anism
    -0.68
    Anim
    -0.66
     onlook
    -0.65
    assisted
    -0.64
    inel
    -0.64
    ATS
    -0.62
    OWS
    -0.61
    ercise
    -0.61
    arten
    -0.59
    POSITIVE LOGITS
     knack
    1.38
     tendency
    1.35
     penchant
    1.19
     reputation
    1.18
     propensity
    1.16
     chance
    1.05
     vested
    1.04
     lot
    0.95
     plethora
    0.92
     tremendous
    0.91
    Activations Density 0.133%

    No Known Activations