© 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. 7-RES-JB
    11. 23946
    Prev
    Next
    INDEX
    Explanations

    signatories or endorsers of agreements or statements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to agreements or signatories in a legal or structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Airl
    -0.77
     Revival
    -0.72
     Shore
    -0.60
    uilt
    -0.60
     Herald
    -0.58
    âĺħâĺħ
    -0.58
    enegger
    -0.58
     Rite
    -0.57
     situational
    -0.56
     Patriot
    -0.56
    POSITIVE LOGITS
    hip
    1.84
    hips
    1.61
    paces
    1.46
    pace
    1.23
    ettings
    1.11
    ervatives
    1.08
     thereof
    1.02
    ystem
    0.96
    pring
    0.93
    mith
    0.91
    Activations Density 0.261%

    No Known Activations