© 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. 13632
    Prev
    Next
    INDEX
    Explanations

    proper names mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks in the text

    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
    ĻĤ
    -0.92
    etheless
    -0.74
     lapt
    -0.71
    Ļ½
    -0.71
    İĭ
    -0.69
    ilst
    -0.68
    mediately
    -0.68
    paren
    -0.65
    ailing
    -0.65
    urances
    -0.64
    POSITIVE LOGITS
    /"
    1.23
     Whedon
    0.76
     moniker
    0.75
    Minecraft
    0.73
     ["
    0.72
     motto
    0.71
     ("
    0.69
    >>\
    0.69
     aka
    0.69
    aneers
    0.66
    Activations Density 0.092%

    No Known Activations