© 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
    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. 13589
    Prev
    Next
    INDEX
    Explanations

    words related to physical exercise activities and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to gym activities and related settings

    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
    drawn
    -0.83
     Strait
    -0.78
    angered
    -0.69
    OPLE
    -0.69
    theless
    -0.68
    IBLE
    -0.66
    OVER
    -0.64
     Citizens
    -0.64
     USC
    -0.63
     Rockefeller
    -0.63
    POSITIVE LOGITS
    nas
    1.37
     gym
    1.00
     trainer
    0.92
     trainers
    0.85
     lapt
    0.83
     workout
    0.79
    rats
    0.79
     Gym
    0.78
     corrid
    0.77
    rition
    0.75
    Activations Density 0.007%

    No Known Activations