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. 1-RES-JB
    6. 13694
    Prev
    Next
    INDEX
    Explanations

    words related to granular substances or textures

    oai_token-act-pair · gpt-3.5-turbo

    references to granulated substances or ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Laugh
    -0.68
     starring
    -0.67
     Toll
    -0.67
     Norn
    -0.65
     Standing
    -0.63
     Rex
    -0.63
     Victory
    -0.63
    lihood
    -0.61
     Gutenberg
    -0.61
    suits
    -0.60
    POSITIVE LOGITS
     gran
    1.14
    ular
    1.02
    ularity
    1.00
    acies
    0.92
    ulates
    0.84
    ules
    0.83
    iband
    0.77
    vier
    0.77
    atial
    0.76
    acy
    0.75
    Activations Density 0.006%

    No Known Activations