© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15631
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "over"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "all over" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uary
    -0.71
    acles
    -0.68
    resy
    -0.68
    ãĤº
    -0.67
    Enlarge
    -0.65
    utenberg
    -0.65
    _-
    -0.64
    neum
    -0.64
    tein
    -0.62
    =-=-=-=-=-=-=-=-
    -0.62
    POSITIVE LOGITS
     again
    0.86
     town
    0.80
    roads
    0.80
     Europe
    0.76
    drive
    0.73
    lake
    0.73
    country
    0.73
    iflower
    0.72
     globe
    0.69
     AMERICA
    0.67
    Activations Density 0.042%

    No Known Activations