© 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. 20433
    Prev
    Next
    INDEX
    Explanations

    initials and titles in a format like "A.K." followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific films and their directors or characters

    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
    eric
    -0.66
    çĶŁ
    -0.60
    Bloomberg
    -0.59
    issues
    -0.58
    Poll
    -0.58
     Collider
    -0.56
    ingham
    -0.55
    adobe
    -0.55
     trending
    -0.55
     celebr
    -0.53
    POSITIVE LOGITS
    nee
    0.98
    idding
    0.81
    itsch
    0.80
    ansas
    0.79
    icker
    0.70
    orea
    0.68
    lez
    0.67
    redits
    0.65
    udos
    0.65
    Å¡
    0.65
    Activations Density 0.019%

    No Known Activations