© 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. 19576
    Prev
    Next
    INDEX
    Explanations

    references to activities or locations related to physical exercise, particularly gyms

    oai_token-act-pair · gpt-3.5-turbo

    references to gyms and gym-related activities

    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
     Strait
    -0.77
    drawn
    -0.74
    */(
    -0.67
    angered
    -0.67
    better
    -0.66
    OPLE
    -0.66
    IBLE
    -0.65
     flawed
    -0.64
    theless
    -0.61
     afar
    -0.61
    POSITIVE LOGITS
    nas
    1.48
     gym
    0.89
    rats
    0.83
     trainer
    0.82
     lapt
    0.81
    bell
    0.81
     Gym
    0.79
    rition
    0.76
     tremend
    0.74
    entary
    0.74
    Activations Density 0.006%

    No Known Activations