© 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. 21166
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that indicate evidence or demonstration of something

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating evidence or examples of performance or capability

    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
    Synopsis
    -0.68
    quire
    -0.68
    ographs
    -0.67
    ãĥ¼ãĥ«
    -0.64
    ibrary
    -0.64
    panel
    -0.62
    kj
    -0.60
    heading
    -0.59
    isition
    -0.59
    laughter
    -0.59
    POSITIVE LOGITS
     versatility
    0.88
     resilience
    0.87
     ingenuity
    0.80
     seriousness
    0.80
     maturity
    0.80
     willingness
    0.78
     persever
    0.72
     teamwork
    0.72
     patience
    0.72
     true
    0.72
    Activations Density 0.373%

    No Known Activations