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. 8-RES-JB
    6. 5205
    Prev
    Next
    INDEX
    Explanations

    mentions of "bi-" prefixes in words

    oai_token-act-pair · gpt-3.5-turbo

    references to biotechnology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.86
    MENTS
    -0.76
    */(
    -0.71
    swick
    -0.69
    inho
    -0.68
     Rack
    -0.66
     grasping
    -0.66
    FUL
    -0.65
     Gibraltar
    -0.64
     Brees
    -0.64
    POSITIVE LOGITS
    weekly
    1.33
    ochem
    1.26
    ographical
    1.23
    ochemistry
    1.20
    otechnology
    1.20
    odynamic
    1.20
    ographies
    1.19
    ocide
    1.18
    omed
    1.14
    omes
    1.10
    Activations Density 0.016%

    No Known Activations