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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15226
    Prev
    Next
    INDEX
    Explanations

    words related to data collection and potentially privacy violations

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, specifically the word "and."

    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
    icago
    -0.77
    YY
    -0.76
    blogspot
    -0.75
    ItemThumbnailImage
    -0.74
     Porsche
    -0.74
    iates
    -0.73
    enne
    -0.71
    apesh
    -0.70
     HDL
    -0.68
    iator
    -0.68
    POSITIVE LOGITS
    TPPStreamerBot
    0.72
    opers
    0.66
    aler
    0.66
     Jefferson
    0.64
    ollah
    0.63
     tumble
    0.62
     nurture
    0.61
    ometric
    0.61
     ink
    0.60
    alcohol
    0.60
    Activations Density 0.240%

    No Known Activations