© 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. 11-RES-JB
    11. 20424
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing to receive information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to news and information dissemination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.76
     Comet
    -0.61
    RESULTS
    -0.61
    MpServer
    -0.59
    nces
    -0.58
    raph
    -0.56
    roph
    -0.56
     Colomb
    -0.54
     Toad
    -0.53
     Pok
    -0.53
    POSITIVE LOGITS
    inion
    0.68
    grave
    0.58
     inbox
    0.56
     delivered
    0.53
    inki
    0.53
    igue
    0.52
    oval
    0.52
    iability
    0.51
    deal
    0.51
    isode
    0.51
    Activations Density 0.054%

    No Known Activations