© 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. 3148
    Prev
    Next
    INDEX
    Explanations

    keywords related to monitoring or keeping tabs on something, particularly in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    the word "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 @ 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
    atern
    -0.74
    doms
    -0.67
     advent
    -0.65
    GAN
    -0.65
    aples
    -0.64
    Ann
    -0.62
    aternity
    -0.61
    OV
    -0.61
    aspberry
    -0.58
    asus
    -0.58
    POSITIVE LOGITS
     tracks
    1.26
    track
    1.23
     track
    1.23
     Tracks
    1.22
    tracks
    1.12
     Track
    1.02
    Track
    0.98
    course
    0.90
    masters
    0.86
    balls
    0.85
    Activations Density 0.013%

    No Known Activations