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. 10-RES-JB
    6. 9834
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers, particularly those resembling phone numbers or contact details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hump
    -0.62
     Arabian
    -0.61
     fray
    -0.60
     pressing
    -0.60
     emph
    -0.59
     topping
    -0.58
     grip
    -0.58
     bearings
    -0.58
     chase
    -0.58
     touching
    -0.57
    POSITIVE LOGITS
    325
    0.97
    232
    0.97
    221
    0.97
    222
    0.96
    224
    0.95
    225
    0.95
    323
    0.92
    324
    0.91
    227
    0.91
    228
    0.91
    Activations Density 0.018%

    No Known Activations