© 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. 23539
    Prev
    Next
    INDEX
    Explanations

    names of people with specific characteristics or connections

    oai_token-act-pair · gpt-3.5-turbo

    mentions of unique or special individuals in a specific context

    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
     eleph
    -0.97
    VERS
    -0.70
    ©¶æ
    -0.70
    accompan
    -0.70
     teasp
    -0.69
     carbohyd
    -0.69
    ¥ŀ
    -0.68
    PDATE
    -0.66
     conserv
    -0.65
     TRANS
    -0.64
    POSITIVE LOGITS
    e
    1.27
    a
    1.25
    o
    1.22
    i
    1.10
    y
    1.10
    ic
    1.02
    ei
    1.01
    an
    0.95
    er
    0.93
    aq
    0.93
    Activations Density 0.223%

    No Known Activations