© 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. 19391
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating a difference between two entities or aspects

    oai_token-act-pair · gpt-3.5-turbo

    instances of comparison

    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
     Polo
    -0.70
    authorized
    -0.64
    aptic
    -0.60
     Epidem
    -0.60
    adia
    -0.58
     recess
    -0.57
    izen
    -0.56
    STAR
    -0.55
    ulas
    -0.55
    bin
    -0.54
    POSITIVE LOGITS
     favorably
    0.92
     thereto
    0.86
    icut
    0.77
     to
    0.73
     favour
    0.70
    Compare
    0.69
    PsyNetMessage
    0.66
    lihood
    0.66
    aneously
    0.66
     Compare
    0.64
    Activations Density 0.029%

    No Known Activations