© 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. 7-RES-JB
    11. 15228
    Prev
    Next
    INDEX
    Explanations

    mentions of competition or conflict between different entities

    oai_token-act-pair · gpt-3.5-turbo

    references to competition or conflict between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olia
    -0.72
    oglobin
    -0.71
    overe
    -0.69
    mans
    -0.68
    umn
    -0.68
    UX
    -0.66
    ux
    -0.64
    acht
    -0.63
    acca
    -0.63
    aughter
    -0.63
    POSITIVE LOGITS
    ries
    1.45
     rival
    0.95
     rivals
    0.92
     factions
    0.89
     competitor
    0.81
     challengers
    0.81
     bidder
    0.76
     viewpoints
    0.76
    rous
    0.74
     competitors
    0.74
    Activations Density 0.033%

    No Known Activations