© 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. 11-RES-JB
    11. 7484
    Prev
    Next
    INDEX
    Explanations

    mentions of various professions or fields of work

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "the" in various contexts related to professions and transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omever
    -0.81
    pers
    -0.70
    Results
    -0.69
    CVE
    -0.67
    Screenshot
    -0.67
     secondly
    -0.66
    contained
    -0.66
    iew
    -0.66
    Timeout
    -0.66
    teness
    -0.66
    POSITIVE LOGITS
     priesthood
    1.30
     profession
    1.25
     workforce
    1.20
     professions
    1.14
     ranks
    1.04
     army
    0.99
     military
    0.97
     Army
    0.96
     academy
    0.92
     Marines
    0.91
    Activations Density 0.230%

    No Known Activations