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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17831
    Prev
    Next
    INDEX
    Explanations

    instances of the word "forced"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "forced."

    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
     Prediction
    -0.62
    orkshire
    -0.61
    izoph
    -0.59
    pport
    -0.58
     Purpose
    -0.55
     Offense
    -0.54
     Potential
    -0.54
    igans
    -0.53
     Worth
    -0.53
     NCT
    -0.52
    POSITIVE LOGITS
     into
    1.12
     onto
    0.91
     to
    0.90
     INTO
    0.86
     awake
    0.86
     thereto
    0.85
    into
    0.81
    tto
    0.81
     aback
    0.81
     out
    0.77
    Activations Density 0.043%

    No Known Activations