© 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. 8-RES-JB
    11. 2493
    Prev
    Next
    INDEX
    Explanations

    sequences of random characters with no apparent pattern or meaning

    oai_token-act-pair · gpt-3.5-turbo

    sequences of characters or symbols that could represent codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     msec
    -0.63
    DonaldTrump
    -0.60
     derog
    -0.57
     abbrevi
    -0.57
    emort
    -0.56
     intentionally
    -0.54
     holiday
    -0.54
     correctly
    -0.54
     caring
    -0.54
     vacuum
    -0.53
    POSITIVE LOGITS
    dq
    0.89
    XM
    0.88
    ZX
    0.87
    CN
    0.85
    zx
    0.84
    qq
    0.84
    wr
    0.84
    Fu
    0.83
    fb
    0.81
    "><
    0.81
    Activations Density 0.036%

    No Known Activations