© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5862
    Prev
    Next
    INDEX
    Explanations

    specific dates and proper nouns, especially related to political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and associated contexts

    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
    âĢ¦âĢ¦
    -0.20
    ´
    -0.20
     Allaah
    -0.19
    ÂŃ
    -0.19
    ,
    -0.18
     ye
    -0.18
    âĢ¦..
    -0.18
    ths
    -0.17
    Âł
    -0.17
     –
    -0.17
    POSITIVE LOGITS
    ThumbnailImage
    0.28
    senal
    0.26
    ActionCode
    0.24
    DeliveryDate
    0.23
    isSpecial
    0.23
    Nitrome
    0.23
    Orderable
    0.23
    ¥ŀ
    0.23
    StreamerBot
    0.23
    ě
    0.22
    Activations Density 12.427%

    No Known Activations