© 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. 18644
    Prev
    Next
    INDEX
    Explanations

    keywords related to military, politics, and government

    oai_token-act-pair · gpt-3.5-turbo

    references to veterans and American identity

    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
    iser
    -0.63
    packing
    -0.62
     True
    -0.60
    mith
    -0.59
     Kut
    -0.58
     whichever
    -0.57
     Oo
    -0.57
     Spokane
    -0.56
    keeper
    -0.55
     touch
    -0.54
    POSITIVE LOGITS
    an
    2.12
    ans
    2.05
    anism
    1.90
    aned
    1.74
    anic
    1.53
    aning
    1.52
    AN
    1.50
    ANS
    1.47
    anus
    1.45
    anical
    1.40
    Activations Density 0.149%

    No Known Activations