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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 8286
    Prev
    Next
    INDEX
    Explanations

    words related to competition and competitors

    oai_token-act-pair · gpt-3.5-turbo

    references to competitors in a business context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oho
    -0.69
    Hat
    -0.69
    oÄŁ
    -0.65
    erd
    -0.65
     Hat
    -0.65
    stones
    -0.64
    olia
    -0.64
    det
    -0.63
    elt
    -0.61
    ttp
    -0.61
    POSITIVE LOGITS
     competitor
    1.08
     competitors
    1.04
     foe
    0.82
     rivals
    0.80
     competing
    0.79
     incumb
    0.78
     contestant
    0.78
     vying
    0.76
     challengers
    0.76
     contestants
    0.75
    Activations Density 0.010%

    No Known Activations