© 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. 10-RES-JB
    11. 16651
    Prev
    Next
    INDEX
    Explanations

    titles or names of various media or software releases

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" indicating a focus on singular subjects or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Versions
    -0.81
    APD
    -0.81
    ['
    -0.81
    daq
    -0.75
    Alien
    -0.74
    Aim
    -0.74
    runners
    -0.73
    models
    -0.72
    Jar
    -0.71
    Ultimately
    -0.71
    POSITIVE LOGITS
     versatile
    1.06
     recurring
    0.96
     fictional
    0.95
     slang
    0.94
     wonderful
    0.94
     unique
    0.94
     wonderfully
    0.93
     powerful
    0.93
     lightweight
    0.93
     fantastic
    0.93
    Activations Density 0.149%

    No Known Activations