© 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. 2248
    Prev
    Next
    INDEX
    Explanations

    terms related to judiciary and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and unique identifiers

    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
    rows
    -0.77
    rew
    -0.76
    hover
    -0.72
    rav
    -0.72
    hold
    -0.71
    ells
    -0.70
    pipe
    -0.70
    born
    -0.69
    risk
    -0.69
    votes
    -0.69
    POSITIVE LOGITS
     metic
    0.66
     treasury
    0.63
     legend
    0.63
    ciating
    0.63
     referen
    0.63
    ļéĨĴ
    0.63
     audience
    0.63
    ciation
    0.60
     millenn
    0.59
     subtitles
    0.59
    Activations Density 0.285%

    No Known Activations