© 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. 3-RES-JB
    11. 1567
    Prev
    Next
    INDEX
    Explanations

    mentions of police reports or claims of violence

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter "M."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¡
    -0.81
     Eleven
    -0.68
    DragonMagazine
    -0.68
    gerald
    -0.65
     yours
    -0.64
     fashioned
    -0.64
     vacant
    -0.63
     tipped
    -0.63
     begg
    -0.63
     tips
    -0.62
    POSITIVE LOGITS
    uppet
    1.09
    ixed
    1.06
    useum
    1.02
    iscal
    1.02
    uzzle
    1.02
    oses
    1.01
    ambo
    1.01
    ISSION
    1.01
    OST
    1.00
    aternal
    0.99
    Activations Density 0.064%

    No Known Activations