© 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. 10407
    Prev
    Next
    INDEX
    Explanations

    negative statements or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases indicating the absence or lack of something

    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
    furt
    -0.84
    estamp
    -0.74
    ãĥĺ
    -0.72
    ĨĴ
    -0.71
    thood
    -0.70
    met
    -0.69
    wich
    -0.66
    û
    -0.64
    court
    -0.64
     filib
    -0.63
    POSITIVE LOGITS
    anan
    0.75
     already
    0.72
    inka
    0.64
    lamm
    0.62
     occasionally
    0.60
     plenty
    0.59
    ttes
    0.59
     shudder
    0.58
     also
    0.58
    RAG
    0.57
    Activations Density 0.198%

    No Known Activations