© 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. 11182
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals, particularly photographers and journalists

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly related to people and organizations

    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
    luaj
    -0.68
    omorphic
    -0.67
    patient
    -0.64
    mbuds
    -0.64
    regulation
    -0.63
    âĵĺ
    -0.61
    appointed
    -0.61
    licted
    -0.59
    %:
    -0.57
     perenn
    -0.56
    POSITIVE LOGITS
     Photography
    1.06
     Jr
    0.95
     /
    0.87
     IMAGES
    0.85
     Contribut
    0.84
    Jr
    0.83
    ulton
    0.83
     Random
    0.83
     III
    0.81
     Archive
    0.81
    Activations Density 0.113%

    No Known Activations