© 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. 4-RES-JB
    11. 23700
    Prev
    Next
    INDEX
    Explanations

    references to the public or public-related matters

    oai_token-act-pair · gpt-3.5-turbo

    references to the public and public opinion

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

    No Comments

    Negative Logits
    Pg
    -0.77
    imov
    -0.72
    RANT
    -0.72
    ansas
    -0.67
    aundering
    -0.67
    okemon
    -0.67
    kson
    -0.66
    wered
    -0.66
    ï¸
    -0.65
    nesota
    -0.64
    POSITIVE LOGITS
    relations
    0.86
     relations
    0.84
     servants
    0.82
     opinion
    0.80
     appetite
    0.80
     broadcaster
    0.79
     outcry
    0.77
    ãĥ¤
    0.76
     affairs
    0.76
    ised
    0.75
    Activations Density 0.041%

    No Known Activations