© 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. 11112
    Prev
    Next
    INDEX
    Explanations

    words related to compounds or composite aspects

    oai_token-act-pair · gpt-3.5-turbo

    the word "comp" and its various forms, indicating a focus on concepts related to compounding or cumulative effects

    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
     whites
    -0.67
     Millennium
    -0.66
    ggle
    -0.64
     Roses
    -0.64
     Spectrum
    -0.60
     Reich
    -0.60
     friendships
    -0.59
     Bul
    -0.58
    FORE
    -0.58
     Rabbit
    -0.57
    POSITIVE LOGITS
    artments
    1.51
    endium
    1.49
    ulsive
    1.39
    ounding
    1.26
    unction
    1.25
    actor
    1.25
    ilers
    1.24
    ressive
    1.22
    ortment
    1.22
    ressing
    1.19
    Activations Density 0.012%

    No Known Activations