© 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. 6-RES-JB
    11. 3528
    Prev
    Next
    INDEX
    Explanations

    references to locations or events related to coastal areas

    oai_token-act-pair · gpt-3.5-turbo

    references to coastal regions and related organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parenthood
    -0.78
    chy
    -0.74
    BuyableInstoreAndOnline
    -0.73
    Lens
    -0.71
    VK
    -0.69
    thood
    -0.67
    DonaldTrump
    -0.66
     Machina
    -0.65
    chel
    -0.64
     Marketable
    -0.62
    POSITIVE LOGITS
    lines
    1.12
     coast
    0.91
    line
    0.90
    guard
    0.85
    yard
    0.84
     Coast
    0.81
    guards
    0.80
    side
    0.80
    esian
    0.75
     shore
    0.74
    Activations Density 0.020%

    No Known Activations