© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11384
    Prev
    Next
    INDEX
    Explanations

    terms related to terms of service and legal agreements

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and specific formatting elements associated with legal or regulatory text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lier
    -0.70
    veland
    -0.67
    worldly
    -0.61
    fts
    -0.61
    ideshow
    -0.60
    ahl
    -0.60
    é¾
    -0.59
    pires
    -0.59
    algia
    -0.57
    eah
    -0.57
    POSITIVE LOGITS
     namely
    1.43
     including
    1.31
     Including
    1.17
     wherein
    1.17
     whereby
    1.14
     thereby
    1.10
     irrespective
    1.09
     which
    1.08
    including
    1.06
     excluding
    1.05
    Activations Density 0.359%

    No Known Activations