© 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. 8-RES-JB
    11. 17701
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals who work as columnists

    oai_token-act-pair · gpt-3.5-turbo

    references to writers and commentators, particularly columnists and bloggers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zik
    -0.74
    fw
    -0.73
    angan
    -0.69
     Territories
    -0.67
     Confederation
    -0.66
    ierrez
    -0.65
     Pradesh
    -0.65
     paperwork
    -0.64
    arching
    -0.63
    ateral
    -0.63
    POSITIVE LOGITS
     laureate
    1.22
     columnist
    0.98
    blogs
    0.94
     extraord
    0.94
    osphere
    0.92
    itatively
    0.90
     blogger
    0.88
     Pamela
    0.86
     Jonah
    0.85
     magazine
    0.84
    Activations Density 0.070%

    No Known Activations