© 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. 8476
    Prev
    Next
    INDEX
    Explanations

    defined terms related to mathematical references and articles

    oai_token-act-pair · gpt-3.5-turbo

    references to academic or scientific citations

    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
    ohydrate
    -0.68
    ritch
    -0.67
    RON
    -0.64
    utic
    -0.63
    ee
    -0.62
    bies
    -0.62
    ohyd
    -0.62
    ERAL
    -0.60
    neys
    -0.60
    haul
    -0.59
    POSITIVE LOGITS
    enance
    0.90
    ais
    0.83
    auga
    0.81
    uality
    0.79
    matic
    0.77
     Kislyak
    0.76
    acca
    0.76
    eous
    0.74
    cean
    0.73
    omatic
    0.73
    Activations Density 0.073%

    No Known Activations