© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 12069
    Prev
    Next
    INDEX
    Explanations

    phrases related to wheezing or respiratory conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "whee," indicating excitement or enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ographers
    -0.79
    EMBER
    -0.79
     Scotia
    -0.76
    pmwiki
    -0.71
    istic
    -0.69
     Defenders
    -0.69
    istically
    -0.69
     Gallery
    -0.67
    outheastern
    -0.66
    arial
    -0.65
    POSITIVE LOGITS
    esome
    0.97
    ldon
    0.90
    lp
    0.88
    tted
    0.88
    atered
    0.87
    cone
    0.85
    leys
    0.82
     Whe
    0.82
    tons
    0.81
    velt
    0.81
    Activations Density 0.027%

    No Known Activations