© 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. 2226
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "AS" followed by a number from 5 to 10

    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
    atically
    -0.79
    rencies
    -0.67
     tion
    -0.64
    lets
    -0.64
    naire
    -0.64
    selves
    -0.63
    ãĤª
    -0.63
    inder
    -0.62
    isers
    -0.62
    ozyg
    -0.61
    POSITIVE LOGITS
    TERN
    1.15
    ADA
    1.13
    CEPT
    1.13
    OVA
    1.07
    CE
    1.06
    IK
    1.06
    ILE
    1.06
    FU
    1.05
    IM
    1.05
    EC
    1.05
    Activations Density 0.059%

    No Known Activations