© 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. 11283
    Prev
    Next
    INDEX
    Explanations

    titles or sections of stories within a text

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of stories or articles

    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
     fame
    -0.68
     Wee
    -0.64
    agall
    -0.63
    ŃĶ
    -0.63
     Haram
    -0.62
    urous
    -0.62
    0000000000000000
    -0.60
     saf
    -0.60
    ullivan
    -0.58
    ãĥĺãĥ©
    -0.58
    POSITIVE LOGITS
     Continued
    1.06
     continues
    0.90
    telling
    0.89
     Contin
    0.86
    stal
    0.81
    llers
    0.63
     Transcript
    0.61
     highlights
    0.60
     reprinted
    0.60
     CONTIN
    0.60
    Activations Density 0.007%

    No Known Activations