© 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. 9-RES-JB
    11. 2238
    Prev
    Next
    INDEX
    Explanations

    phrases with advice or instructions

    oai_token-act-pair · gpt-3.5-turbo
    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
     constit
    -0.63
    agra
    -0.60
    quin
    -0.59
    swick
    -0.59
    arial
    -0.57
    aced
    -0.56
     center
    -0.56
     prompted
    -0.56
     altogether
    -0.56
     intrig
    -0.55
    POSITIVE LOGITS
     beware
    1.11
     Beware
    1.03
    Always
    1.00
     Always
    0.99
     Avoid
    0.90
    Eat
    0.88
    Avoid
    0.86
     Keep
    0.85
     Stay
    0.84
    Keep
    0.83
    Activations Density 0.385%

    No Known Activations