© 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. 4-RES-JB
    11. 23993
    Prev
    Next
    INDEX
    Explanations

    words related to squatting and strength training

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to squat exercises and their techniques

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

    No Comments

    Negative Logits
     Centauri
    -0.73
     Pandora
    -0.72
     Carbuncle
    -0.72
     Moj
    -0.70
     Editorial
    -0.70
     Aven
    -0.69
     Crimes
    -0.68
     Orwell
    -0.68
     Governments
    -0.67
     CSI
    -0.67
    POSITIVE LOGITS
    ercise
    1.14
     squats
    1.14
     workout
    1.11
     workouts
    1.02
     exercises
    1.01
     Technique
    0.99
    ERC
    0.98
    Training
    0.97
     gymn
    0.93
     physique
    0.93
    Activations Density 0.166%

    No Known Activations