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. 22344
    Prev
    Next
    INDEX
    Explanations

    phrases related to bulk items or quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or collections of items

    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
     Enemies
    -0.71
    pires
    -0.71
     Judges
    -0.67
     Children
    -0.67
    entric
    -0.65
     Strateg
    -0.64
    uers
    -0.64
     Schools
    -0.63
    endants
    -0.63
    gypt
    -0.63
    POSITIVE LOGITS
     bulk
    0.92
    efully
    0.73
     shipments
    0.73
    haul
    0.71
     shipment
    0.71
     omn
    0.70
     quota
    0.70
    achusetts
    0.69
     bins
    0.69
     haul
    0.69
    Activations Density 0.012%

    No Known Activations