© 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. 6749
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    references to funding, compliance, and legal or administrative issues

    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
     realise
    -0.73
    ãĥİ
    -0.67
     civilisation
    -0.67
     realised
    -0.63
     humour
    -0.61
    ãĥ¼ãĥĨãĤ£
    -0.60
     colourful
    -0.59
     manoeuv
    -0.59
     flavours
    -0.59
     endeavour
    -0.59
    POSITIVE LOGITS
    .")
    1.24
    .;
    1.19
     ."
    1.18
    .]
    1.16
    ."[
    1.15
    .}
    1.15
    ."
    1.11
    .)
    1.03
    .'"
    1.02
    ;"
    1.02
    Activations Density 0.828%

    No Known Activations