© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14407
    Prev
    Next
    INDEX
    Explanations

    personal development and self-improvement affirmations

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to individuals or groups in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Helm
    -0.75
     Outside
    -0.68
    Newsletter
    -0.67
     Peak
    -0.61
     Via
    -0.60
    Enlarge
    -0.59
     Techniques
    -0.59
     Option
    -0.57
     Camp
    -0.57
     Pair
    -0.57
    POSITIVE LOGITS
    cause
    0.90
    chy
    0.88
    ching
    0.79
    ÃĥÃĤ
    0.76
    tis
    0.75
    'll
    0.73
    ngth
    0.72
    self
    0.71
    just
    0.70
    itsu
    0.69
    Activations Density 0.191%

    No Known Activations