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. 3-RES-JB
    6. 22206
    Prev
    Next
    INDEX
    Explanations

    words related to negative attributes or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "ugliness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.95
    ingham
    -0.93
    aver
    -0.90
    idential
    -0.89
    owder
    -0.86
    akings
    -0.83
    uther
    -0.82
    cedented
    -0.81
    OTA
    -0.79
    ortium
    -0.77
    POSITIVE LOGITS
     ugly
    1.11
     adolesc
    0.83
     elephant
    0.80
     crap
    0.77
     beasts
    0.77
     spectacle
    0.76
     fallout
    0.75
     glare
    0.71
     fades
    0.71
     barb
    0.70
    Activations Density 0.006%

    No Known Activations