© 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. 0-RES-JB
    11. 22593
    Prev
    Next
    INDEX
    Explanations

    expressions related to explicit content

    oai_token-act-pair · gpt-3.5-turbo

    references to explicit content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    town
    -0.82
    weather
    -0.72
    mare
    -0.68
    luck
    -0.67
     Quarter
    -0.64
     brings
    -0.63
     quarters
    -0.63
    yrs
    -0.62
    south
    -0.62
    ley
    -0.61
    POSITIVE LOGITS
     explicit
    3.56
     implicit
    2.03
     explicitly
    1.80
     Explicit
    1.66
     unamb
    1.45
     implicitly
    1.34
     unequiv
    1.30
     overtly
    1.24
     ambiguous
    1.18
     blatant
    1.10
    Activations Density 0.017%

    No Known Activations