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. 1476
    Prev
    Next
    INDEX
    Explanations

    phrases that denote a composition or makeup of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote composition or structure

    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
    bury
    -0.76
    bell
    -0.65
     squared
    -0.63
     Kard
    -0.62
     Scotia
    -0.62
    Water
    -0.62
    duc
    -0.61
    Sounds
    -0.60
    ilings
    -0.59
    Pear
    -0.58
    POSITIVE LOGITS
     consisted
    1.18
     consist
    1.14
     consists
    1.12
     comprised
    1.02
     consisting
    0.95
     chiefly
    0.89
    alion
    0.87
    ģ«
    0.86
     solely
    0.85
    ĸļ
    0.83
    Activations Density 0.008%

    No Known Activations