© 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. 1025
    Prev
    Next
    INDEX
    Explanations

    keywords related to dependencies and reliance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reliance or dependence

    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
    efer
    -0.82
    ²¾
    -0.79
    ific
    -0.79
    iser
    -0.76
    furt
    -0.75
    mberg
    -0.75
    itz
    -0.74
    ulton
    -0.74
    Ĥ¬
    -0.73
    wagen
    -0.73
    POSITIVE LOGITS
    encies
    1.18
    ency
    1.01
     upon
    0.78
     dependency
    0.75
     injection
    0.72
    leness
    0.72
    cipline
    0.69
    doms
    0.68
     cooker
    0.67
    ministic
    0.66
    Activations Density 0.037%

    No Known Activations