© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22383
    Prev
    Next
    INDEX
    Explanations

    statements indicating correctness or agreement

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements regarding correctness or approval

    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
    inese
    -0.67
    improve
    -0.66
    VERTISEMENT
    -0.65
    ravings
    -0.64
     Pastebin
    -0.62
    ifle
    -0.62
    insula
    -0.61
    cients
    -0.60
    ictionary
    -0.60
    umble
    -0.59
    POSITIVE LOGITS
     surpr
    0.70
    going
    0.69
    emn
    0.69
     understatement
    0.69
    quartered
    0.69
    wic
    0.68
    ingly
    0.67
    inently
    0.66
     enough
    0.65
    enko
    0.63
    Activations Density 0.345%

    No Known Activations