© 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. 10121
    Prev
    Next
    INDEX
    Explanations

    references to actions related to a shower

    oai_token-act-pair · gpt-3.5-turbo

    mentions of showers

    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
    rian
    -0.75
    folios
    -0.67
     Dominion
    -0.66
    ravel
    -0.65
    cius
    -0.64
    sem
    -0.64
    sup
    -0.63
    interest
    -0.62
     Libertarian
    -0.61
    verage
    -0.60
    POSITIVE LOGITS
     showers
    1.00
    ysis
    0.92
     curtain
    0.90
    ing
    0.90
    robe
    0.87
     shower
    0.86
    ennes
    0.81
     ashore
    0.79
    issance
    0.78
    atur
    0.77
    Activations Density 0.008%

    No Known Activations