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. 18108
    Prev
    Next
    INDEX
    Explanations

    prefixes "pre-"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "pre-" relating to preparation or pre-existing conditions

    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
     Ago
    -0.62
     sidelines
    -0.61
     Ukrain
    -0.59
     Rex
    -0.58
    IBLE
    -0.58
     misunderstood
    -0.57
     rooting
    -0.56
     whis
    -0.55
     loophole
    -0.55
     Trend
    -0.54
    POSITIVE LOGITS
    fecture
    1.40
    requisites
    1.35
    achers
    1.32
    lude
    1.32
    occup
    1.31
    occupied
    1.24
    cludes
    1.22
    emption
    1.20
    fect
    1.20
    cession
    1.17
    Activations Density 0.020%

    No Known Activations