© 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. 9-RES-JB
    11. 7114
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences or URLs starting with 'http' and 'www'

    oai_token-act-pair · gpt-3.5-turbo

    technical identifiers, possibly related to programming or data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATIVE
    -0.85
    ALLY
    -0.85
    IZE
    -0.78
     CONTROL
    -0.75
     scrut
    -0.72
    LESS
    -0.70
    FUL
    -0.69
     LIFE
    -0.69
     Alley
    -0.68
    OUS
    -0.67
    POSITIVE LOGITS
    cs
    1.13
    pd
    1.12
    gs
    1.08
    fp
    1.08
    fs
    1.08
    cd
    1.07
    cc
    1.07
    cf
    1.05
    wx
    1.05
    cb
    1.05
    Activations Density 0.132%

    No Known Activations