© 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. 10-RES-JB
    11. 1011
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a statement or position being communicated

    oai_token-act-pair · gpt-3.5-turbo

    indications, statements, or signals related to political or governmental actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctors
    -0.65
     Digest
    -0.64
    anon
    -0.63
    EStreamFrame
    -0.61
    fen
    -0.61
     wast
    -0.60
    avery
    -0.60
    irc
    -0.59
     Recap
    -0.59
    iru
    -0.58
    POSITIVE LOGITS
     repeatedly
    1.19
     publicly
    1.04
     unequivocally
    0.99
     willingness
    0.94
     explicitly
    0.93
     emphatically
    0.91
     intention
    0.91
     intentions
    0.86
     since
    0.83
     openly
    0.82
    Activations Density 0.200%

    No Known Activations