© 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. 2281
    Prev
    Next
    INDEX
    Explanations

    references to drafts or preliminary versions of documents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "draft" in various contexts

    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
    zzi
    -0.73
     destro
    -0.70
    Ĭ±
    -0.69
    tics
    -0.68
    cellence
    -0.67
    ILLE
    -0.67
    SEE
    -0.67
     fortun
    -0.67
    phasis
    -0.66
    cles
    -0.64
    POSITIVE LOGITS
    smanship
    1.56
    Kings
    0.97
     draft
    0.91
     drafts
    0.86
     dod
    0.84
     legislation
    0.74
     outline
    0.72
     PowerPoint
    0.72
    furt
    0.71
     guidelines
    0.70
    Activations Density 0.042%

    No Known Activations