© 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. 1-RES-JB
    11. 9547
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or teams that are strong competitors or candidates in a given context

    oai_token-act-pair · gpt-3.5-turbo

    the term "contender" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imar
    -0.74
    erie
    -0.72
    Ku
    -0.71
    romy
    -0.70
    arching
    -0.68
    ahon
    -0.68
    engineering
    -0.66
    att
    -0.66
    jer
    -0.66
    carry
    -0.65
    POSITIVE LOGITS
     contender
    1.51
     contenders
    1.36
     frontrunner
    1.06
     challengers
    1.04
     contestant
    0.97
     competitor
    0.94
     challenger
    0.93
     finalists
    0.90
     contestants
    0.88
     candidates
    0.85
    Activations Density 0.009%

    No Known Activations