© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24449
    Prev
    Next
    INDEX
    Explanations

    self-introductions

    oai_token-act-pair · gpt-3.5-turbo

    personal introductions and self-descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aptic
    -0.87
     decreasing
    -0.80
     diminishing
    -0.78
     decreases
    -0.77
     erosion
    -0.74
     lowering
    -0.74
    effect
    -0.73
    Decre
    -0.73
    delay
    -0.71
     paralysis
    -0.71
    POSITIVE LOGITS
     belong
    1.03
     belonged
    1.00
     resided
    0.92
     enrolled
    0.88
     participated
    0.86
    Born
    0.82
     origin
    0.81
     maj
    0.81
     Born
    0.81
     reside
    0.81
    Activations Density 0.739%

    No Known Activations