© 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. 11031
    Prev
    Next
    INDEX
    Explanations

    adjectives describing size or quantity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence of quantities or sizes, particularly focusing on the word "a" to signal limited or small amounts

    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
    lees
    -0.73
    asks
    -0.72
    anto
    -0.68
    boards
    -0.67
    angelo
    -0.63
    also
    -0.63
    mos
    -0.62
    anti
    -0.62
    anism
    -0.60
    grounds
    -0.58
    POSITIVE LOGITS
     handful
    1.66
     few
    1.53
     fraction
    1.34
     couple
    1.29
     subset
    1.20
    few
    1.18
     tiny
    1.12
     single
    1.11
     small
    1.10
     curs
    1.09
    Activations Density 0.146%

    No Known Activations