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. 8-RES-JB
    6. 14667
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of 'picking'

    oai_token-act-pair · gpt-3.5-turbo

    references to "Pick" or "pick up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sea
    -0.75
    english
    -0.72
     TAG
    -0.71
    CTV
    -0.71
    BAT
    -0.64
    cess
    -0.61
    DEBUG
    -0.61
     Presence
    -0.61
    isf
    -0.61
    âĸ¬
    -0.60
    POSITIVE LOGITS
    axe
    1.36
    pocket
    1.31
    eting
    1.24
    eters
    1.12
    aign
    1.08
    ering
    1.00
    ety
    1.00
    ett
    0.93
    ets
    0.92
    eter
    0.91
    Activations Density 0.028%

    No Known Activations