© 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. 3-RES-JB
    11. 23991
    Prev
    Next
    INDEX
    Explanations

    phrases related to appropriateness and correctness in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "appropriate" and related contextual discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.75
    ching
    -0.75
    roid
    -0.75
    plane
    -0.73
    cipl
    -0.70
    chet
    -0.70
    rix
    -0.70
    peak
    -0.69
    gun
    -0.69
     Plane
    -0.69
    POSITIVE LOGITS
    appropriate
    0.88
    appropriately
    0.86
    ively
    0.84
     guiActiveUn
    0.82
     punishment
    0.81
     amounts
    0.80
     appropriation
    0.80
     punishments
    0.80
     Appropri
    0.79
    tarian
    0.77
    Activations Density 0.015%

    No Known Activations