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. 7-RES-JB
    6. 22316
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Cer" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and terms related to a specific location or entity, especially "Cer" as in "Cerro."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urst
    -0.75
     Barkley
    -0.70
    ers
    -0.70
    erella
    -0.68
    ãĥĥãĥĪ
    -0.67
     Buffett
    -0.67
    ĸļ
    -0.65
     Fever
    -0.65
    erences
    -0.65
     Strauss
    -0.64
    POSITIVE LOGITS
    bal
    1.04
    berus
    1.04
    rors
    1.04
    vette
    1.02
    der
    1.00
    nec
    0.96
    amic
    0.95
    sei
    0.93
    rera
    0.92
    rible
    0.92
    Activations Density 0.058%

    No Known Activations