Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19107
    Prev
    Next
    INDEX
    Explanations

    words related to wild or extreme behaviors

    oai_token-act-pair · gpt-3.5-turbo

    the term "crazy" used in various contexts

    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
    Reviewed
    -0.96
    tein
    -0.82
    ãĥĺãĥ©
    -0.81
    ribut
    -0.81
    uter
    -0.81
    fman
    -0.80
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.79
    lain
    -0.78
    lected
    -0.76
    adr
    -0.74
    POSITIVE LOGITS
     crazy
    0.75
     nuts
    0.73
     shit
    0.72
    spawn
    0.70
     beasts
    0.68
     chic
    0.68
     overboard
    0.68
    astically
    0.67
     antics
    0.67
     fringe
    0.66
    Activations Density 0.015%

    No Known Activations