© 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. 878
    Prev
    Next
    INDEX
    Explanations

    calls to action or instructions directed towards the reader, such as clicking a box or helping

    oai_token-act-pair · gpt-3.5-turbo

    elements related to user verification processes online

    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
    ãĥ´
    -0.66
    ufact
    -0.63
     perspect
    -0.62
    cius
    -0.58
    phen
    -0.56
     Pros
    -0.55
     comprise
    -0.55
    pert
    -0.53
     graded
    -0.52
    ccording
    -0.51
    POSITIVE LOGITS
     buttons
    0.78
    ãģı
    0.70
     Invalid
    0.70
    interstitial
    0.67
    Capt
    0.67
    boats
    0.65
    ause
    0.64
     button
    0.63
     anymore
    0.62
    ĵ
    0.61
    Activations Density 0.035%

    No Known Activations