© 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 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. 7431
    Prev
    Next
    INDEX
    Explanations

    references to the creation or sharing of creative projects and activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article 'a' and phrases indicating quantity or a specific item

    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
    anism
    -0.71
    independence
    -0.71
    onto
    -0.70
    âĢİ
    -0.68
    AIDS
    -0.67
    scl
    -0.65
     occup
    -0.65
    independent
    -0.65
    Contents
    -0.64
    agher
    -0.63
    POSITIVE LOGITS
     bunch
    1.57
     lot
    1.56
     couple
    1.52
     few
    1.40
     LOT
    1.37
     nice
    1.24
     HUGE
    1.21
     bit
    1.21
     pretty
    1.14
     ton
    1.14
    Activations Density 0.360%

    No Known Activations