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. 9-RES-JB
    6. 21512
    Prev
    Next
    INDEX
    Explanations

    computer software and technology-related terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of technical products, systems, and academic or security contexts

    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
    anon
    -0.73
     Cheong
    -0.63
    venants
    -0.63
    leon
    -0.63
     Moff
    -0.62
     Activate
    -0.61
    gall
    -0.61
    heid
    -0.61
    lves
    -0.59
    llah
    -0.58
    POSITIVE LOGITS
     purposes
    1.86
     sake
    1.78
    ummies
    1.06
     reasons
    1.01
     purpose
    0.95
     lovers
    0.82
     beginners
    0.73
     foreseeable
    0.73
     reason
    0.73
     duration
    0.72
    Activations Density 0.845%

    No Known Activations