© 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. 2-RES-JB
    11. 12977
    Prev
    Next
    INDEX
    Explanations

    specific mentions of 'Lake'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Lake" and its references to various locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nir
    -0.80
    imental
    -0.78
     tremend
    -0.75
    */(
    -0.74
    endiary
    -0.73
    STEM
    -0.73
    ————
    -0.71
    AAAAAAAA
    -0.70
    binary
    -0.70
    ulate
    -0.69
    POSITIVE LOGITS
     Erie
    1.04
     Lake
    1.03
     Lakes
    0.95
     Superior
    0.88
     lake
    0.86
     trout
    0.86
     Falls
    0.86
     Pond
    0.84
     Nile
    0.84
     Ranch
    0.83
    Activations Density 0.006%

    No Known Activations