© 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. 7-RES-JB
    11. 17254
    Prev
    Next
    INDEX
    Explanations

    the word "thought" followed by a high confidence level

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinion or judgment about movies

    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
    kw
    -0.74
    conservancy
    -0.69
    ç«
    -0.67
    iona
    -0.64
     PLUS
    -0.63
    versions
    -0.62
    Naz
    -0.61
    acerb
    -0.60
    osures
    -0.60
    Footnote
    -0.59
    POSITIVE LOGITS
    fully
    1.00
    lessly
    0.94
    fulness
    0.89
    ij士
    0.72
     Catalog
    0.71
    ileaks
    0.67
     Archdemon
    0.66
    ful
    0.66
     Parks
    0.65
    culus
    0.64
    Activations Density 0.054%

    No Known Activations