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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5324
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal institutions or proceedings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "court" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curfew
    -0.69
    AMI
    -0.64
    OV
    -0.63
     Franks
    -0.58
     hol
    -0.58
    ocalypse
    -0.56
    ARK
    -0.56
    ORN
    -0.56
     Shining
    -0.55
     warp
    -0.54
    POSITIVE LOGITS
    tyard
    1.66
    thouse
    1.28
    ser
    1.19
    ses
    1.18
    sers
    1.16
    tes
    1.12
    ten
    1.10
    tesy
    1.10
    gue
    1.08
    rier
    1.07
    Activations Density 0.053%

    No Known Activations