© 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. 14134
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "from"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "from" indicating a range or variety of subjects or entities

    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
    é¾įåĸļ士
    -0.83
    sic
    -0.81
    isode
    -0.75
    itivity
    -0.74
    resy
    -0.72
    win
    -0.71
    correct
    -0.70
    imil
    -0.69
    endant
    -0.69
    ivist
    -0.67
    POSITIVE LOGITS
     afar
    0.97
     lowly
    0.93
     beginner
    0.89
     humble
    0.88
     beginners
    0.83
     mild
    0.82
     novice
    0.82
     toddlers
    0.81
     cradle
    0.81
     kindergarten
    0.79
    Activations Density 0.074%

    No Known Activations