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. 7-RES-JB
    6. 10257
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations and titles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various organizational structures and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pesh
    -0.70
    âĵĺ
    -0.67
    rawdownloadcloneembedreportprint
    -0.62
    issan
    -0.58
    Merit
    -0.58
    SPONSORED
    -0.57
     Fukushima
    -0.57
    steamapps
    -0.56
     Harden
    -0.56
     Mechdragon
    -0.56
    POSITIVE LOGITS
     historian
    0.61
     insiders
    0.55
     Underworld
    0.55
     hierarchy
    0.53
    topia
    0.53
     Handbook
    0.53
     rookies
    0.53
    crim
    0.53
     Edge
    0.52
    justice
    0.52
    Activations Density 0.868%

    No Known Activations