Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17519
    Prev
    Next
    INDEX
    Explanations

    references to the word "track"

    oai_token-act-pair · gpt-3.5-turbo

    references to "track" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.74
     pand
    -0.72
    osate
    -0.67
    acco
    -0.66
    oresc
    -0.65
    ately
    -0.64
    aples
    -0.61
    AIN
    -0.60
    untu
    -0.59
     Saga
    -0.56
    POSITIVE LOGITS
    suit
    1.14
    tracks
    1.09
    track
    1.02
    suits
    1.01
    ball
    0.98
    pad
    0.94
    balls
    0.94
    side
    0.93
    masters
    0.92
    runner
    0.90
    Activations Density 0.017%

    No Known Activations