© 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. 7-RES-JB
    11. 1892
    Prev
    Next
    INDEX
    Explanations

    adjectives describing appearance or condition

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives indicating quality or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mental
    -0.75
    ricular
    -0.75
     Childhood
    -0.70
    byter
    -0.69
    shire
    -0.65
    iculty
    -0.63
    selling
    -0.61
    igion
    -0.60
    ritical
    -0.60
     submission
    -0.59
    POSITIVE LOGITS
     lifeless
    0.79
    bones
    0.79
    bley
    0.79
     suspic
    0.74
     sleek
    0.73
     ugly
    0.72
     shiny
    0.70
    pretty
    0.69
     differently
    0.69
     suspicious
    0.69
    Activations Density 0.144%

    No Known Activations