© 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. 9-RES-JB
    11. 17241
    Prev
    Next
    INDEX
    Explanations

    instances of the word "admit" and related terms in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "admit" or variations related to acknowledgment of truth or mistakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Liber
    -0.75
    ANN
    -0.74
    icles
    -0.73
    ENN
    -0.72
    CLUS
    -0.72
    ERT
    -0.72
    wark
    -0.69
    lake
    -0.66
     ................
    -0.66
    ubi
    -0.65
    POSITIVE LOGITS
     mistakes
    1.32
     mistake
    1.11
     underest
    1.00
     errors
    0.97
     underestimated
    0.97
     shortcomings
    0.94
     mishand
    0.93
     regrets
    0.90
     imperfect
    0.88
     unintentionally
    0.87
    Activations Density 0.188%

    No Known Activations