Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6-RES-JB
    6. 10190
    Prev
    Next
    INDEX
    Explanations

    the verb "pick" followed by a noun or preposition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pick" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peria
    -0.76
    CTV
    -0.75
    interrupted
    -0.74
    brance
    -0.71
    itement
    -0.71
    cess
    -0.71
    clair
    -0.70
    orescence
    -0.68
    acion
    -0.67
    Sea
    -0.66
    POSITIVE LOGITS
    pocket
    1.22
    axe
    1.20
    eting
    1.09
    eters
    0.88
    picking
    0.88
     pick
    0.81
    pick
    0.80
    osition
    0.80
    ety
    0.80
    ozy
    0.79
    Activations Density 0.030%

    No Known Activations