© 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. 10-RES-JB
    11. 20541
    Prev
    Next
    INDEX
    Explanations

    profanity and offensive language

    oai_token-act-pair · gpt-3.5-turbo

    affirmations or denials within discussion contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curfew
    -0.35
     dams
    -0.32
     earthquakes
    -0.31
     genomes
    -0.31
     bases
    -0.30
     reactors
    -0.30
     pores
    -0.30
     polygamy
    -0.29
     jails
    -0.29
     roofs
    -0.28
    POSITIVE LOGITS
    orp
    0.35
    perty
    0.35
    icably
    0.35
    Ax
    0.35
    uine
    0.33
    orne
    0.33
    omew
    0.33
     Helpful
    0.32
    REDACTED
    0.32
    ohn
    0.32
    Activations Density 2.058%

    No Known Activations