© 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. 3-RES-JB
    11. 6505
    Prev
    Next
    INDEX
    Explanations

    words related to tubs or tub-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to containers, specifically tubs and jugs

    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
     lockout
    -0.72
     Marketable
    -0.68
    pend
    -0.63
     relativity
    -0.61
     Universities
    -0.61
     Wildcats
    -0.61
     CBD
    -0.60
     conscious
    -0.60
     ABV
    -0.59
     Flavoring
    -0.59
    POSITIVE LOGITS
    ular
    1.26
    tub
    1.06
    eless
    1.01
    elight
    0.96
     tub
    0.93
    marine
    0.91
    emade
    0.90
    atile
    0.88
    ules
    0.88
    ility
    0.87
    Activations Density 0.005%

    No Known Activations