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. 0-RES-JB
    6. 3085
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities and legal processes

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Warfare
    -0.57
     Created
    -0.57
    FTWARE
    -0.54
     Settings
    -0.53
     dismantle
    -0.53
     churn
    -0.53
    é¾įå¥ij士
    -0.52
    #$
    -0.51
     buoy
    -0.50
     wealthier
    -0.50
    POSITIVE LOGITS
    in
    3.47
    ins
    1.89
    IN
    1.73
    inian
    1.71
    inet
    1.62
    inia
    1.61
    inic
    1.55
    inis
    1.53
    inen
    1.51
    inos
    1.48
    Activations Density 0.049%

    No Known Activations