© 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. 4-RES-JB
    11. 10079
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data, computing, and specifications

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to military agreements and organizations

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

    No Comments

    Negative Logits
    ãģĨ
    -0.55
    govtrack
    -0.52
    adr
    -0.51
     corrid
    -0.51
    ModLoader
    -0.49
     GOODMAN
    -0.49
    æĺ¯
    -0.49
    omething
    -0.48
    Ĥª
    -0.47
    ¯
    -0.46
    POSITIVE LOGITS
     --------------------
    0.78
    malink
    0.60
     Includes
    0.58
     ----------------
    0.57
     https
    0.55
     mins
    0.51
     --------------------------------
    0.51
     avail
    0.50
     -----
    0.50
     LTD
    0.50
    Activations Density 1.050%

    No Known Activations