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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 7813
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating approval or authorization

    oai_token-act-pair · gpt-3.5-turbo

    the term "signed off" in various contexts, indicating approval or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     liter
    -0.69
    jad
    -0.67
     Rowling
    -0.66
    anan
    -0.65
     Ung
    -0.62
     Faul
    -0.61
    istor
    -0.61
    oved
    -0.61
    ophile
    -0.60
    Gall
    -0.60
    POSITIVE LOGITS
    cffffcc
    0.84
    shoot
    0.75
    MENTS
    0.73
    tank
    0.71
    rection
    0.71
    ussions
    0.69
    ¯¯
    0.68
    WARNING
    0.67
    points
    0.63
    igious
    0.63
    Activations Density 0.039%

    No Known Activations