© 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. 16645
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computational algorithms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "diff" and its variations, indicating a focus on differences or difficulty levels in a context

    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
    FUL
    -0.78
    ÃįÃį
    -0.74
    ctica
    -0.74
    matic
    -0.74
     Redemption
    -0.72
    matically
    -0.71
    CHO
    -0.71
    tto
    -0.69
    ocene
    -0.69
    crow
    -0.69
    POSITIVE LOGITS
    icult
    1.46
    iculty
    1.25
    erence
    1.10
    erences
    1.10
    idence
    1.07
    inished
    1.06
    raction
    1.04
    racted
    0.95
    ering
    0.94
    eren
    0.94
    Activations Density 0.035%

    No Known Activations