© 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 EvalsExportsinterp-engineNEWAPI 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. 9682
    Prev
    Next
    INDEX
    Explanations

    strings of numbers within a specific range, particularly those with repeated values

    oai_token-act-pair · gpt-3.5-turbo

    numeric entries, likely related to identifiers or statistical values

    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
    anooga
    -0.91
     millenn
    -0.91
    querque
    -0.81
     tremend
    -0.76
    ¥ŀ
    -0.74
     nomine
    -0.71
    reon
    -0.71
     exha
    -0.71
     compan
    -0.70
    hya
    -0.69
    POSITIVE LOGITS
    504
    0.87
    .............
    0.84
    502
    0.83
    309
    0.81
    806
    0.81
    641
    0.81
    007
    0.81
    608
    0.81
    756
    0.80
    503
    0.80
    Activations Density 0.063%

    No Known Activations