© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3939
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Pick" at various positions within words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Pick" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    english
    -0.81
     Antar
    -0.67
    ctic
    -0.66
    eatures
    -0.66
     rotor
    -0.65
    ILLE
    -0.64
    nsic
    -0.62
     anthem
    -0.62
     grounds
    -0.62
    ROR
    -0.62
    POSITIVE LOGITS
     Pick
    1.36
    Pick
    1.21
    axe
    1.15
    pick
    1.07
    ering
    1.03
     Picks
    0.98
    athon
    0.93
    pocket
    0.92
    asso
    0.88
    picking
    0.87
    Activations Density 0.011%

    No Known Activations