© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 22307
    Prev
    Next
    INDEX
    Explanations

    words related to cleanliness or precision

    oai_token-act-pair · gpt-3.5-turbo

    recurring patterns or themes related to clumsiness or awkwardness

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

    No Comments

    Negative Logits
    awaru
    -0.78
    Ô
    -0.71
    chwitz
    -0.70
    BALL
    -0.69
     Territory
    -0.69
     Mutual
    -0.69
    tumblr
    -0.67
    BIP
    -0.67
    GMT
    -0.67
    terday
    -0.66
    POSITIVE LOGITS
    amps
    1.21
    amped
    1.17
    ojure
    1.15
    ipper
    1.13
    ogged
    1.04
    uster
    0.99
    ippers
    0.97
    aps
    0.96
    ashing
    0.95
    oned
    0.95
    Activations Density 0.008%

    No Known Activations