© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 23406
    Prev
    Next
    INDEX
    Explanations

    phone numbers with a specific format

    oai_token-act-pair · gpt-3.5-turbo

    contact numbers and references to customer service

    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
     stacked
    -0.66
     piled
    -0.64
     backdrop
    -0.63
     gears
    -0.61
     lubric
    -0.59
     Carbuncle
    -0.59
     fins
    -0.57
     losers
    -0.57
     stacking
    -0.57
     Musk
    -0.55
    POSITIVE LOGITS
    866
    0.74
    888
    0.74
     pione
    0.73
    877
    0.71
    onut
    0.70
    essage
    0.68
    800
    0.68
    Questions
    0.67
    tips
    0.66
    ohn
    0.66
    Activations Density 0.044%

    No Known Activations