© 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. 1-RES-JB
    11. 2061
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of being wrong or doing something incorrectly

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wrong" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivities
    -0.75
    istration
    -0.70
    andals
    -0.68
    mop
    -0.68
    mable
    -0.68
    aments
    -0.64
    amaz
    -0.64
    inar
    -0.64
    asis
    -0.62
    sburg
    -0.60
    POSITIVE LOGITS
     Wrong
    1.20
    Correct
    0.82
    ected
    0.78
    wrong
    0.76
    Wr
    0.73
     Isles
    0.72
    nown
    0.71
     unfocusedRange
    0.71
    backer
    0.71
     Misc
    0.70
    Activations Density 0.005%

    No Known Activations