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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6893
    Prev
    Next
    INDEX
    Explanations

    phrases related to job titles or roles

    oai_token-act-pair · gpt-3.5-turbo

    instances of individuals associated with co-founding or leadership roles in various organizations

    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
     Tsukuyomi
    -0.78
     decency
    -0.74
     context
    -0.73
     Vengeance
    -0.72
     caveats
    -0.72
     kindness
    -0.71
     trem
    -0.71
     DRAG
    -0.70
     intact
    -0.69
     Gauntlet
    -0.69
    POSITIVE LOGITS
    founder
    2.02
    author
    1.72
    director
    1.72
    owner
    1.72
    creator
    1.70
    chair
    1.66
    host
    1.60
    authored
    1.58
    found
    1.58
    worker
    1.57
    Activations Density 0.022%

    No Known Activations