© 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. 23857
    Prev
    Next
    INDEX
    Explanations

    words related to conflict or confrontation

    oai_token-act-pair · gpt-3.5-turbo

    information related to significant geological events and their impacts

    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
     ÂŃ
    -0.78
     Arabic
    -0.65
     enrol
    -0.65
     enroll
    -0.61
     bilingual
    -0.60
     Afghan
    -0.60
    natureconservancy
    -0.59
    graduate
    -0.59
    amazon
    -0.58
    Education
    -0.58
    POSITIVE LOGITS
     tremend
    0.95
     shenan
    0.91
     infamous
    0.88
     somew
    0.85
     horrend
    0.83
    ãĥ¯ãĥ³
    0.83
     Cth
    0.82
     perished
    0.82
     unlucky
    0.80
     tragically
    0.79
    Activations Density 1.309%

    No Known Activations