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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 20340
    Prev
    Next
    INDEX
    Explanations

    the word "select" in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "select" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andowski
    -0.79
    dad
    -0.75
    MpServer
    -0.68
     eru
    -0.64
    orem
    -0.64
     spilled
    -0.62
    ena
    -0.62
    é¾
    -0.62
    urd
    -0.61
     Strikes
    -0.61
    POSITIVE LOGITS
     select
    3.77
    select
    2.36
     Select
    2.34
    Select
    2.19
     selects
    2.11
     selected
    2.05
     selecting
    1.94
     SELECT
    1.79
    selected
    1.73
     selection
    1.71
    Activations Density 0.018%

    No Known Activations