© 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. 23771
    Prev
    Next
    INDEX
    Explanations

    references to specific policy centers and studies

    oai_token-act-pair · gpt-3.5-turbo

    references to policy-related institutions and studies

    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
     captcha
    -0.84
    soever
    -0.69
    WAY
    -0.68
    mind
    -0.64
     incidentally
    -0.63
     mechan
    -0.62
    cause
    -0.62
    thumbnails
    -0.62
     labour
    -0.62
    ITNESS
    -0.62
    POSITIVE LOGITS
     Analyst
    0.89
     Analysis
    0.88
    edia
    0.80
     Advoc
    0.77
     Agency
    0.76
     Strategies
    0.76
    edIn
    0.76
     Analy
    0.75
     Fund
    0.75
     Insight
    0.73
    Activations Density 0.071%

    No Known Activations