© 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. 8-RES-JB
    11. 16897
    Prev
    Next
    INDEX
    Explanations

    references to inductions or honors in various halls of fame

    oai_token-act-pair · gpt-3.5-turbo

    references to the Hall of Fame across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alam
    -0.79
    selves
    -0.77
    cos
    -0.76
    resp
    -0.70
    onal
    -0.67
    apest
    -0.67
    forth
    -0.66
    weeney
    -0.66
    wise
    -0.66
    pher
    -0.64
    POSITIVE LOGITS
     Fame
    1.08
     induction
    1.02
     induct
    0.88
     Trophy
    0.86
    brance
    0.86
     honors
    0.84
     plaque
    0.81
     Bowl
    0.80
     Awards
    0.79
    spective
    0.78
    Activations Density 0.028%

    No Known Activations