© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 7038
    Prev
    Next
    INDEX
    Explanations

    words related to controversial or sensitive topics

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific characters or themes in storytelling

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

    No Comments

    Negative Logits
    aign
    -0.85
    atform
    -0.81
    iated
    -0.77
    rowth
    -0.76
    iations
    -0.75
    iation
    -0.75
    roups
    -0.75
    resh
    -0.74
    igor
    -0.73
    agne
    -0.73
    POSITIVE LOGITS
    ãĥĥãĥĪ
    0.78
     nuns
    0.77
    essee
    0.75
     paws
    0.70
     Pupp
    0.69
     Cly
    0.67
     chefs
    0.67
    eness
    0.67
    fix
    0.66
    culosis
    0.64
    Activations Density 0.025%

    No Known Activations