© 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 EvalsExportsinterp-engineNEWAPI 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. 23160
    Prev
    Next
    INDEX
    Explanations

    individuals described with personal information, such as age, profession, achievements, and personal stories

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "who" in relation to various subjects or characters

    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
    âĵĺ
    -0.69
    CONCLUS
    -0.69
    ulp
    -0.65
    VO
    -0.65
    ¥µ
    -0.64
    dfx
    -0.64
    Something
    -0.63
    akedown
    -0.62
    é¾įå¥ij士
    -0.62
    ADE
    -0.61
    POSITIVE LOGITS
     underwent
    1.14
     suffers
    1.00
     earns
    0.97
     wears
    0.95
     undergo
    0.94
     admits
    0.94
     wore
    0.93
     grew
    0.92
     suffered
    0.92
     graduated
    0.91
    Activations Density 0.102%

    No Known Activations