© 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. 6-RES-JB
    11. 14599
    Prev
    Next
    INDEX
    Explanations

    words related to chemical reactions or physical actions like movements or responses

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reactions and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holders
    -0.92
    holder
    -0.79
    abwe
    -0.67
    ppo
    -0.66
    luster
    -0.66
    berman
    -0.63
    holding
    -0.63
     councils
    -0.61
     Anthem
    -0.60
     Panasonic
    -0.60
    POSITIVE LOGITS
    ivated
    0.95
    itect
    0.94
    ivation
    0.90
    ivity
    0.88
    ivating
    0.88
    ency
    0.82
    anooga
    0.81
    ors
    0.80
     Native
    0.75
    DOM
    0.75
    Activations Density 0.019%

    No Known Activations