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. 9-RES-JB
    6. 19200
    Prev
    Next
    INDEX
    Explanations

    environmental elements such as locations including caves, mountains, lakes, and specific physical objects

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of locations, items, or categories related to consumer goods and services

    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
    noon
    -0.62
    ãĥį
    -0.60
     Tycoon
    -0.60
    PDATE
    -0.60
     Neighbor
    -0.57
     circumstance
    -0.57
    é¾į
    -0.56
    Operation
    -0.54
     Hyp
    -0.54
     Investigator
    -0.53
    POSITIVE LOGITS
     etc
    1.41
    hips
    1.01
    etc
    1.01
    mith
    1.00
    paces
    0.96
     &
    0.91
    folk
    0.89
    poons
    0.84
    â̦)
    0.82
    ,
    0.82
    Activations Density 0.185%

    No Known Activations