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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-RES-JB
    6. 10314
    Prev
    Next
    INDEX
    Explanations

    coastal locations or references in text

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations along coastlines

    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
    chel
    -0.92
    VL
    -0.84
    thood
    -0.74
    Lens
    -0.74
    728
    -0.73
    chy
    -0.70
    Bir
    -0.68
     Flavoring
    -0.68
    Beer
    -0.67
    iencies
    -0.67
    POSITIVE LOGITS
     coast
    1.13
     shore
    0.93
     Coast
    0.86
    side
    0.81
    lines
    0.78
     coasts
    0.77
     shores
    0.75
     coastline
    0.75
     cliffs
    0.75
     Bahamas
    0.72
    Activations Density 0.008%

    No Known Activations