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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8096
    Prev
    Next
    INDEX
    Explanations

    words related to train tracks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tracks"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ALLY
    -0.67
     Iro
    -0.65
     Islanders
    -0.65
    icultural
    -0.62
     Kinnikuman
    -0.61
     Nordic
    -0.61
     Spartan
    -0.60
     Dominican
    -0.59
    Ann
    -0.59
    agons
    -0.59
    POSITIVE LOGITS
     tracks
    1.22
     Tracks
    1.20
    tracks
    1.07
    heet
    1.02
    track
    0.93
    geist
    0.87
    Upload
    0.86
    schild
    0.86
    pace
    0.84
    mith
    0.82
    Activations Density 0.013%

    No Known Activations