© 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. 2-RES-JB
    11. 22414
    Prev
    Next
    INDEX
    Explanations

    phrases indicating confession or admission of a negative action or behavior

    oai_token-act-pair · gpt-3.5-turbo

    the word "admitted" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chn
    -0.77
    printed
    -0.71
    otor
    -0.71
     chimpan
    -0.70
    eled
    -0.65
     enthus
    -0.64
    pleting
    -0.63
    andel
    -0.63
    asu
    -0.63
    ammy
    -0.62
    POSITIVE LOGITS
     Admission
    0.91
     admitting
    0.89
     admitted
    0.87
    ibility
    0.84
     admit
    0.79
    IBLE
    0.79
     admission
    0.79
     admits
    0.76
     wrongdoing
    0.74
    ilty
    0.68
    Activations Density 0.014%

    No Known Activations