© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 10076
    Prev
    Next
    INDEX
    Explanations

    references to draft documents and guidelines

    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 @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spears
    -0.69
    rians
    -0.68
    cles
    -0.68
    zzi
    -0.67
     destro
    -0.67
    Ĭ±
    -0.66
    rian
    -0.66
    Sea
    -0.66
    phasis
    -0.66
    pert
    -0.66
    POSITIVE LOGITS
    smanship
    1.64
    Kings
    0.94
     dod
    0.88
     drafts
    0.84
     draft
    0.83
     muster
    0.71
     outline
    0.70
     manuscript
    0.68
     script
    0.67
     screenplay
    0.67
    Activations Density 0.048%

    No Known Activations