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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 10944
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "pick" followed by a number indicating preference or selection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'pick' in various contexts

    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
    moral
    -0.74
    interrupted
    -0.70
    brance
    -0.70
    itement
    -0.68
    enture
    -0.68
    isSpecialOrderable
    -0.68
    issance
    -0.67
    senal
    -0.65
    Sea
    -0.65
    peria
    -0.64
    POSITIVE LOGITS
    axe
    1.28
    pocket
    1.19
    eting
    1.02
    pick
    0.95
    picking
    0.93
     pick
    0.92
     axe
    0.84
    ety
    0.78
    eters
    0.78
    athon
    0.78
    Activations Density 0.018%

    No Known Activations