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. 20845
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the location "Eleven Madison Park."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the number "eleven" and its various contexts

    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
     Kimber
    -0.88
     bas
    -0.70
    lde
    -0.65
    BER
    -0.65
     Tas
    -0.64
    ãĥĵ
    -0.64
    bp
    -0.62
    imore
    -0.61
     prone
    -0.61
    transform
    -0.60
    POSITIVE LOGITS
     Eleven
    4.07
     Twelve
    1.73
     eleven
    1.41
    Ele
    1.33
     Sevent
    1.27
    elve
    1.15
     Fif
    1.12
     Stranger
    1.10
    irteen
    1.01
    arya
    1.00
    Activations Density 0.060%

    No Known Activations