© 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. 7-RES-JB
    11. 2683
    Prev
    Next
    INDEX
    Explanations

    numeric values or codes within text

    oai_token-act-pair · gpt-3.5-turbo

    specific references to script or programming-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.59
    Ire
    -0.59
    aird
    -0.54
     nep
    -0.54
     nodd
    -0.54
    romeda
    -0.52
    inence
    -0.51
     enthusi
    -0.50
    swer
    -0.49
    vertising
    -0.49
    POSITIVE LOGITS
     Strategies
    0.56
    )</
    0.53
     Awakens
    0.52
     |--
    0.51
     ->
    0.47
     *)
    0.47
     kills
    0.46
     |
    0.46
     Phant
    0.45
     âĻ
    0.45
    Activations Density 1.127%

    No Known Activations