© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1704
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of expressing an opinion or refusal

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the act of speaking or expressing oneself

    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
    ockets
    -0.71
    gotten
    -0.60
     infl
    -0.59
     peninsula
    -0.57
     Nanto
    -0.57
     instincts
    -0.56
     Peninsula
    -0.56
    aspx
    -0.56
    edia
    -0.55
     Firearms
    -0.54
    POSITIVE LOGITS
     goodbye
    1.68
     hello
    1.41
     Goodbye
    1.30
     farewell
    1.25
     hi
    1.18
     yes
    1.11
     sorry
    1.11
     aloud
    1.09
     Amen
    1.08
     YES
    0.98
    Activations Density 0.119%

    No Known Activations