© 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. 11-RES-JB
    11. 17720
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used for emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the presence of punctuation marks and emoticons, indicating a casual or humorous tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conversions
    -0.82
     conversion
    -0.72
     immersion
    -0.66
     fraction
    -0.65
     biomass
    -0.63
     lifetime
    -0.62
     vault
    -0.60
     descending
    -0.60
     contacts
    -0.59
     transc
    -0.58
    POSITIVE LOGITS
    -)
    1.29
    rolley
    1.20
    -(
    1.18
    lol
    1.14
    ))))
    1.13
    ((
    1.08
    D
    1.08
    _>
    1.07
    ::::::::
    1.07
    DD
    1.06
    Activations Density 0.075%

    No Known Activations