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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6537
    Prev
    Next
    INDEX
    Explanations

    words related to colors and materials

    oai_token-act-pair · gpt-3.5-turbo

    negative connotations or descriptors related to color or material

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dickinson
    -0.74
     Norris
    -0.74
     Confederation
    -0.73
     GamerGate
    -0.73
     Rica
    -0.72
    ulhu
    -0.72
     Patron
    -0.72
     FML
    -0.69
     Discipline
    -0.68
     Fiscal
    -0.67
    POSITIVE LOGITS
    based
    1.32
    shaped
    1.13
    themed
    1.12
    eyed
    1.12
    haired
    1.12
    clad
    1.11
    induced
    1.11
    covered
    1.09
    colored
    1.09
    derived
    1.07
    Activations Density 0.151%

    No Known Activations