© 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. 8-RES-JB
    11. 1266
    Prev
    Next
    INDEX
    Explanations

    terms related to various occupations or designations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to problem-solving, legitimacy, and various societal structures

    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
    athi
    -0.73
     Chronicle
    -0.69
     excerpt
    -0.68
     infographic
    -0.62
     snippet
    -0.60
     accompanying
    -0.60
     fabricated
    -0.60
     Economist
    -0.59
     handmade
    -0.59
     Rodrigo
    -0.58
    POSITIVE LOGITS
    livion
    1.22
     mode
    1.03
    thood
    1.03
     parity
    0.96
    arenthood
    0.93
     immortality
    0.88
    practice
    0.86
     heaven
    0.84
     status
    0.83
     obscurity
    0.79
    Activations Density 0.595%

    No Known Activations