© 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. 0-RES-JB
    11. 8372
    Prev
    Next
    INDEX
    Explanations

    words related to mistakes or errors

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "blunders"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mosqu
    -0.80
    kell
    -0.75
     scrut
    -0.73
     inference
    -0.73
    ascript
    -0.71
    parser
    -0.71
    atical
    -0.70
    yout
    -0.69
    uminati
    -0.69
    idav
    -0.67
    POSITIVE LOGITS
    ľ
    0.74
     Clancy
    0.71
     Flight
    0.66
     Halls
    0.66
     Shy
    0.65
     Sloan
    0.64
     POLITICO
    0.64
    Ĭ±
    0.64
     Guardians
    0.63
     Ler
    0.63
    Activations Density 0.000%

    No Known Activations