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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 13838
    Prev
    Next
    INDEX
    Explanations

    keywords related to training and education

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "training" and related 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
    gets
    -0.70
     Vox
    -0.68
     á
    -0.66
    sm
    -0.66
    neum
    -0.65
     Meier
    -0.64
    olls
    -0.62
    Minecraft
    -0.62
    eph
    -0.61
    nav
    -0.60
    POSITIVE LOGITS
     training
    1.02
     Training
    0.96
    Training
    0.95
     Peaks
    0.92
    training
    0.84
     workouts
    0.82
     instructors
    0.81
     veter
    0.79
    ÃįÃį
    0.78
    GGGGGGGG
    0.78
    Activations Density 0.021%

    No Known Activations