Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21046
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "bracing" or variations like "braced" or "braces"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "brag."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ended
    -0.66
     Phoenix
    -0.63
     functioning
    -0.60
     lying
    -0.60
     Salvation
    -0.58
     shut
    -0.57
     polio
    -0.57
     warrants
    -0.56
     Dexter
    -0.56
     namely
    -0.56
    POSITIVE LOGITS
    acing
    1.37
    imming
    1.35
    aced
    1.25
    idal
    1.21
    istle
    1.21
    ash
    1.17
    onz
    1.14
    agged
    1.12
    acers
    1.11
    icked
    1.11
    Activations Density 0.012%

    No Known Activations