© 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. 8065
    Prev
    Next
    INDEX
    Explanations

    contact information such as phone numbers and email addresses

    oai_token-act-pair · gpt-3.5-turbo

    contact information and numerical references related to communication

    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
     Slate
    -0.67
     successive
    -0.61
     topping
    -0.61
     letters
    -0.60
     Dickinson
    -0.58
     tug
    -0.58
     navigating
    -0.58
     dealing
    -0.57
     rid
    -0.57
     dipping
    -0.57
    POSITIVE LOGITS
    2020
    1.15
    4000
    1.14
    3000
    1.11
    8000
    1.08
    2200
    1.07
    1800
    1.07
    6000
    1.06
    0200
    1.06
    9999
    1.05
    5000
    1.05
    Activations Density 0.020%

    No Known Activations