© 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. 8-RES-JB
    11. 21157
    Prev
    Next
    INDEX
    Explanations

    phrases related to upward or downward movement or change

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hierarchical structures and actions of raising or lowering standards

    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
    clave
    -0.66
    iuses
    -0.64
    izon
    -0.63
    matter
    -0.63
    SOURCE
    -0.61
    gans
    -0.60
    vier
    -0.59
    sylv
    -0.58
    deal
    -0.58
    zig
    -0.57
    POSITIVE LOGITS
     stakes
    1.08
     ceilings
    1.03
     prices
    1.02
     expectations
    1.01
     altitude
    1.01
     levels
    0.99
     temperatures
    0.98
     heights
    0.97
     temperature
    0.94
     eyebrows
    0.90
    Activations Density 0.383%

    No Known Activations