© 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. 2-RES-JB
    11. 17884
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitive racing events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of races and racing events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.94
    ogle
    -0.78
    argon
    -0.76
    olia
    -0.76
    odder
    -0.72
    erva
    -0.71
    ipher
    -0.71
    initions
    -0.70
    thora
    -0.66
    urances
    -0.66
    POSITIVE LOGITS
     races
    1.06
     race
    1.05
     Races
    1.03
    horse
    0.99
    Race
    0.98
    course
    0.97
     Race
    0.95
    bike
    0.92
     racing
    0.86
    cars
    0.85
    Activations Density 0.018%

    No Known Activations