© 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. 11-RES-JB
    11. 14981
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong preference or support for something, such as being a fan or an advocate

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong support or enthusiasm for various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atography
    -0.69
    BILITIES
    -0.68
    代
    -0.67
    Edited
    -0.67
    classes
    -0.67
    mology
    -0.67
    AMY
    -0.67
    hops
    -0.67
    illions
    -0.66
    NetMessage
    -0.66
    POSITIVE LOGITS
     supporter
    1.57
     proponent
    1.56
     believer
    1.44
     admire
    1.39
     advocate
    1.33
     adherent
    1.26
     backer
    1.17
     critic
    1.13
     follower
    1.13
     opponent
    1.12
    Activations Density 0.150%

    No Known Activations