© 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. 7816
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numerical values

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and indicators of emphasis or significance

    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
    ascus
    -0.60
    eny
    -0.59
    ritz
    -0.57
     misunder
    -0.56
    nance
    -0.56
     oversaw
    -0.55
    phasis
    -0.55
    oÄŁan
    -0.54
     sanctioned
    -0.53
    tten
    -0.53
    POSITIVE LOGITS
     if
    1.91
    if
    1.75
     If
    1.67
    If
    1.53
     Otherwise
    1.47
    Otherwise
    1.44
     IF
    1.36
    else
    1.33
     endif
    1.21
    unless
    1.19
    Activations Density 0.203%

    No Known Activations