© 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. 14794
    Prev
    Next
    INDEX
    Explanations

    words related to ownership or possession

    oai_token-act-pair · gpt-3.5-turbo

    plural noun forms, particularly those related to various contexts and subjects

    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
     Maced
    -0.63
     Pharaoh
    -0.61
     Rothschild
    -0.60
     Detail
    -0.60
     Nero
    -0.59
     Tours
    -0.58
     RN
    -0.58
     Jiu
    -0.58
     pressured
    -0.58
     Shy
    -0.58
    POSITIVE LOGITS
    lightly
    1.36
    keleton
    1.29
    ixty
    1.29
    atisf
    1.27
    uddenly
    1.25
    omew
    1.23
    ources
    1.22
    ELF
    1.21
    pecially
    1.21
    leeve
    1.19
    Activations Density 0.193%

    No Known Activations