© 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. 2-RES-JB
    11. 4372
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "breezy" with varying spellings, likely looking for different contexts in which this term is used

    oai_token-act-pair · gpt-3.5-turbo

    words related to lightness or comfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    markets
    -0.85
    sense
    -0.81
    aph
    -0.79
    children
    -0.76
    foreseen
    -0.75
    mers
    -0.74
    omics
    -0.73
    ²¾
    -0.73
    hedral
    -0.71
    oided
    -0.71
    POSITIVE LOGITS
     Bree
    1.15
     breeze
    1.08
     bree
    1.05
    ESH
    0.85
    issance
    0.81
     Brill
    0.80
     Zimmer
    0.76
     refreshing
    0.75
    scill
    0.73
     Sunny
    0.71
    Activations Density 0.023%

    No Known Activations