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. 13062
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantities and physical objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a large quantity or pile of items

    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
    peer
    -0.76
    Commission
    -0.75
    Introduced
    -0.72
    imester
    -0.71
     Presence
    -0.70
    ħĭ
    -0.70
    uca
    -0.69
    ilyn
    -0.69
    Serv
    -0.69
    acus
    -0.67
    POSITIVE LOGITS
     goodies
    1.20
     assorted
    1.02
     rubble
    1.00
     sorts
    0.99
     grapes
    0.97
     bricks
    0.94
     groceries
    0.94
     crap
    0.92
     potatoes
    0.92
     oranges
    0.91
    Activations Density 0.141%

    No Known Activations