© 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. 0-RES-JB
    11. 6725
    Prev
    Next
    INDEX
    Explanations

    references to the phrase "Little [Something]"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "Little"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elig
    -0.76
    ansen
    -0.71
     attrition
    -0.70
     req
    -0.68
    ussen
    -0.68
     chrome
    -0.67
     aggreg
    -0.66
    uru
    -0.65
     forwards
    -0.65
     cruc
    -0.65
    POSITIVE LOGITS
     Little
    3.60
    Little
    2.88
    little
    2.10
     little
    1.33
     Big
    1.26
     Tiny
    1.24
     Darling
    1.17
     Younger
    1.15
    Big
    1.09
     Minute
    1.07
    Activations Density 0.018%

    No Known Activations