© 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 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. 9-RES-JB
    11. 15977
    Prev
    Next
    INDEX
    Explanations

    professional affiliations and career details from resumes or biographies

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and references to collaborative contexts in professional backgrounds

    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
    >[
    -0.82
    irt
    -0.76
    ptoms
    -0.75
    emi
    -0.75
    rium
    -0.71
    ¿½
    -0.70
    ize
    -0.69
    isy
    -0.68
    awks
    -0.68
    ilant
    -0.68
    POSITIVE LOGITS
     oversaw
    1.25
     participated
    1.12
     owns
    0.96
     served
    0.95
     toured
    0.94
     authored
    0.92
     subsequently
    0.91
     oversees
    0.91
     undertook
    0.90
     volunteered
    0.90
    Activations Density 0.309%

    No Known Activations