© 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. 2681
    Prev
    Next
    INDEX
    Explanations

    lines containing the special character 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    sections related to software installation commands and instructions

    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
     Courier
    -0.67
     citiz
    -0.63
    ustom
    -0.61
     Lois
    -0.60
     residences
    -0.60
     Kitty
    -0.57
     footing
    -0.57
     retirees
    -0.57
     ageing
    -0.57
     Spy
    -0.56
    POSITIVE LOGITS
    arta
    0.82
    ̶
    0.80
    igo
    0.79
    Í
    0.78
    ↵
    0.76
    cking
    0.73
    ³³³³³³³³³³³³³³³³
    0.73
    unes
    0.71
    dyl
    0.70
    áµ
    0.70
    Activations Density 0.182%

    No Known Activations