© 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. 1-RES-JB
    11. 20207
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets related to webpage elements, specifically those using the "taboola" element

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax and operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hof
    -0.84
    ulative
    -0.82
    holm
    -0.81
    tones
    -0.74
    æĸ¹
    -0.73
    ulation
    -0.72
    hol
    -0.71
    tone
    -0.69
    apolis
    -0.69
    estate
    -0.69
    POSITIVE LOGITS
     ||
    1.13
    ||||
    1.09
    avascript
    0.87
     [];
    0.86
    ||
    0.79
     @@
    0.68
     Tayyip
    0.67
     |--
    0.65
    {{
    0.65
     !
    0.63
    Activations Density 0.008%

    No Known Activations