© 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. 12-RES-JB
    11. 3303
    Prev
    Next
    INDEX
    Explanations

    horticultural advice related to plants and biodiversity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    strings of symbols and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     WD
    -0.80
     Warren
    -0.73
     Brent
    -0.72
     Ryder
    -0.72
     vampires
    -0.69
     vampire
    -0.69
     Dale
    -0.69
     Benedict
    -0.68
     Jesuit
    -0.68
     Nichols
    -0.67
    POSITIVE LOGITS
    ï
    1.88
     ï
    1.53
    á
    1.49
    âĺ
    1.42
    âķ
    1.36
    ðĿ
    1.33
    â
    1.33
    Û
    1.30
    áµ
    1.29
    ðŁ
    1.28
    Activations Density 0.046%

    No Known Activations