© 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. 4307
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism, reprimand, and negative evaluation

    oai_token-act-pair · gpt-3.5-turbo

    instances of criticism or reprimand

    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
    auga
    -0.77
    uncture
    -0.75
    metics
    -0.72
    IELD
    -0.69
    ortium
    -0.68
    essee
    -0.67
    UE
    -0.65
     nomine
    -0.64
    orno
    -0.63
    opsy
    -0.63
    POSITIVE LOGITS
     ber
    1.17
    keley
    1.16
    anche
    0.77
     Laden
    0.75
    lin
    0.75
    erk
    0.74
    liner
    0.72
    rief
    0.72
    deck
    0.71
     XVI
    0.70
    Activations Density 0.011%

    No Known Activations