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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 10554
    Prev
    Next
    INDEX
    Explanations

    complex and technical language related to mathematics and modeling

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to architecture and structural ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adelphia
    -0.92
     Bravo
    -0.83
     Scream
    -0.77
     Dunk
    -0.76
    Bomb
    -0.75
     Shots
    -0.75
     Lucky
    -0.75
     Bombs
    -0.75
     Celeb
    -0.74
     snapped
    -0.72
    POSITIVE LOGITS
     methodological
    1.41
     epist
    1.38
     empir
    1.36
     philosophers
    1.31
     empirical
    1.27
     presupp
    1.27
     analytic
    1.22
     mathemat
    1.20
     conceptual
    1.20
     theoretical
    1.19
    Activations Density 0.814%

    No Known Activations