© 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. 0-RES-JB
    11. 1067
    Prev
    Next
    INDEX
    Explanations

    terms related to business competition

    oai_token-act-pair · gpt-3.5-turbo

    references to competitors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forgive
    -0.74
    usp
    -0.73
     pardon
    -0.70
     bless
    -0.68
     Rape
    -0.67
    ondon
    -0.67
    UID
    -0.66
    ocument
    -0.64
    herty
    -0.64
    ulet
    -0.64
    POSITIVE LOGITS
     competitors
    3.84
     competitor
    3.28
     rivals
    2.21
     competition
    2.14
     challengers
    1.89
     entrants
    1.86
     competing
    1.85
     contestants
    1.70
     Compet
    1.67
     compete
    1.65
    Activations Density 0.007%

    No Known Activations