© 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. 9-RES-JB
    11. 4262
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating a strong personal stance or belief

    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
    catentry
    -0.82
     Globe
    -0.71
     Ammunition
    -0.68
     Hunting
    -0.66
    elsen
    -0.64
     Sund
    -0.64
     Torrent
    -0.64
    antine
    -0.60
     backdrop
    -0.60
     Sever
    -0.59
    POSITIVE LOGITS
    'll
    1.31
    're
    1.24
    've
    1.17
    'd
    1.15
    'm
    1.07
     belong
    1.01
     owe
    1.00
     shouldn
    0.98
     wouldn
    0.90
     HAVE
    0.89
    Activations Density 0.230%

    No Known Activations