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. 7-RES-JB
    6. 14930
    Prev
    Next
    INDEX
    Explanations

    names or parts of names that include "Pal"

    oai_token-act-pair · gpt-3.5-turbo

    words that reference individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.81
    :{
    -0.74
    OTOS
    -0.68
    REDACTED
    -0.62
    gerald
    -0.60
    glers
    -0.58
    ktop
    -0.56
     Rebell
    -0.56
    ANN
    -0.55
    fee
    -0.54
    POSITIVE LOGITS
    ieri
    0.84
    ophon
    0.78
    encia
    0.75
    ophone
    0.75
    agne
    0.75
    dale
    0.73
     Nieto
    0.73
    ocene
    0.71
    quin
    0.71
    steen
    0.70
    Activations Density 0.106%

    No Known Activations