© 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. 15666
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to admissions of guilt or ownership

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "admit" and its variations, indicating admissions of guilt or truthfulness

    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
     ILCS
    -0.82
    rior
    -0.71
    osi
    -0.70
    ighth
    -0.68
    acements
    -0.67
    atility
    -0.66
    ãĤ¡
    -0.65
    asus
    -0.64
    rouse
    -0.63
    adesh
    -0.63
    POSITIVE LOGITS
     wrongdoing
    1.07
     defeat
    1.01
     guilt
    0.99
     responsibility
    0.78
     ignorance
    0.77
     admitting
    0.77
     mistakes
    0.77
     fault
    0.76
     culp
    0.74
     admit
    0.74
    Activations Density 0.057%

    No Known Activations