© 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. 4-RES-JB
    11. 14540
    Prev
    Next
    INDEX
    Explanations

    the word "frankly" in texts

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing frankness or honesty

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

    No Comments

    Negative Logits
    anwhile
    -0.75
    ammy
    -0.75
    andel
    -0.72
     curfew
    -0.71
    andr
    -0.69
    tein
    -0.68
    eland
    -0.65
     Landing
    -0.65
    aeus
    -0.63
    pel
    -0.63
    POSITIVE LOGITS
    EngineDebug
    0.81
     speaking
    0.78
    odox
    0.75
     disreg
    0.73
     admit
    0.72
     frankly
    0.71
    ãĥĥ
    0.68
     acknowledged
    0.67
    æ©Ł
    0.67
    \\\\\\\\
    0.67
    Activations Density 0.012%

    No Known Activations