© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 10653
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to leadership roles and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to leadership roles, particularly those denoted by the term "chair."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tatt
    -0.77
     IMAGES
    -0.75
     suscept
    -0.67
     Sicily
    -0.66
     conclud
    -0.65
     Collider
    -0.64
     Bagg
    -0.63
     blackmail
    -0.63
     Curve
    -0.63
     Apocalypse
    -0.62
    POSITIVE LOGITS
    manship
    1.77
    woman
    1.75
    person
    1.65
    men
    1.47
    mans
    1.47
    lift
    1.40
    women
    1.39
    pers
    1.27
    man
    1.25
    boards
    1.16
    Activations Density 0.022%

    No Known Activations