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. 3-RES-JB
    6. 10525
    Prev
    Next
    INDEX
    Explanations

    mentions of modern technology, specifically data centers and processors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.83
    adesh
    -0.78
    regor
    -0.77
    udder
    -0.72
    artney
    -0.72
    intent
    -0.70
    Mine
    -0.67
    afort
    -0.67
    hips
    -0.66
    RAFT
    -0.64
    POSITIVE LOGITS
     fut
    1.16
    ility
    0.86
    oleon
    0.80
     unfocusedRange
    0.80
    zel
    0.75
     prolong
    0.73
    chair
    0.69
    acent
    0.69
    onic
    0.68
    inen
    0.68
    Activations Density 0.013%

    No Known Activations