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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20399
    Prev
    Next
    INDEX
    Explanations

    the word "I" followed by a verb indicating intention

    oai_token-act-pair · gpt-3.5-turbo

    the first-person pronoun "I" and related personal references

    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
     Globe
    -0.78
     Nanto
    -0.71
     Leban
    -0.65
    catentry
    -0.64
    stellar
    -0.63
    ãĥ¼ãĤ¯
    -0.63
     Hunting
    -0.63
    eworthy
    -0.63
     Kinn
    -0.60
     Gerard
    -0.59
    POSITIVE LOGITS
    'll
    1.05
    've
    1.05
    'd
    0.97
    're
    0.95
    'm
    0.85
    arers
    0.81
    self
    0.81
     could
    0.79
     owe
    0.78
     shouldn
    0.75
    Activations Density 0.357%

    No Known Activations