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. 17675
    Prev
    Next
    INDEX
    Explanations

    locations or places within a town

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "owning" or possession

    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
     Centauri
    -0.70
     repe
    -0.63
     comparison
    -0.63
     tri
    -0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
     therm
    -0.61
     ultra
    -0.60
     Terms
    -0.60
     ultr
    -0.60
     Presidential
    -0.60
    POSITIVE LOGITS
    own
    5.00
    OWN
    2.59
    owned
    1.46
    owners
    1.32
    ower
    1.31
    owed
    1.31
    owner
    1.28
    Own
    1.25
    ows
    1.25
    owe
    1.17
    Activations Density 0.010%

    No Known Activations