© 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. 3-RES-JB
    11. 13048
    Prev
    Next
    INDEX
    Explanations

    coastal locations or regions within the context of various discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to coastal areas and related geographical features

    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
    sen
    -0.92
     Machina
    -0.85
    chel
    -0.82
    atile
    -0.82
    Downloadha
    -0.78
    VL
    -0.77
    Gene
    -0.75
    enger
    -0.74
    chy
    -0.74
    VP
    -0.73
    POSITIVE LOGITS
     coastal
    0.92
     erosion
    0.92
     seas
    0.85
     inund
    0.84
     waters
    0.83
     cliffs
    0.78
     encl
    0.77
     Coastal
    0.77
     shore
    0.75
     inland
    0.75
    Activations Density 0.007%

    No Known Activations