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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 9898
    Prev
    Next
    INDEX
    Explanations

    the word "wells"

    oai_token-act-pair · gpt-3.5-turbo

    references to wells, particularly in the context of drilling or water supply

    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
    âĶģ
    -0.75
    izophren
    -0.73
    IENCE
    -0.73
    SHIP
    -0.71
    REDACTED
    -0.71
    IENT
    -0.66
    UTH
    -0.66
     recogn
    -0.65
     Disorders
    -0.65
    RAW
    -0.64
    POSITIVE LOGITS
     drilled
    1.03
     wells
    1.01
    chool
    0.88
    inery
    0.85
    ards
    0.84
    rigan
    0.83
    field
    0.81
     groundwater
    0.81
    lings
    0.80
     drilling
    0.80
    Activations Density 0.015%

    No Known Activations