© 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. 11084
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "met" or variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    words related to a variety of "met" terms and their contextual usages

    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
    heit
    -0.67
    Ħ¢
    -0.66
     bleach
    -0.65
     Cinderella
    -0.62
     Grad
    -0.61
     Croat
    -0.60
     beads
    -0.59
     TTL
    -0.58
     Coy
    -0.57
     directions
    -0.57
    POSITIVE LOGITS
    urgy
    0.87
    xual
    0.84
    DragonMagazine
    0.82
    antage
    0.81
    ritic
    0.81
    risis
    0.78
    ãĤ¡
    0.78
    orage
    0.78
    opolis
    0.76
    ysical
    0.75
    Activations Density 0.106%

    No Known Activations