© 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. 2340
    Prev
    Next
    INDEX
    Explanations

    instances of specific numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    instances of situations or events that are characterized by challenges or difficulties

    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
    baugh
    -0.75
    Problem
    -0.67
    ////////
    -0.66
    æ©Ł
    -0.65
    ":[{"
    -0.63
    eret
    -0.63
    igue
    -0.63
    malink
    -0.62
    verning
    -0.62
    ":{"
    -0.62
    POSITIVE LOGITS
     even
    1.21
     downright
    1.09
     outright
    0.97
    even
    0.84
     hundreds
    0.81
     EVEN
    0.77
     entire
    0.76
    undreds
    0.74
     suicide
    0.74
    yond
    0.73
    Activations Density 1.228%

    No Known Activations