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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 24435
    Prev
    Next
    INDEX
    Explanations

    references to a specific geographical location, namely "Rakhine State"

    oai_token-act-pair · gpt-3.5-turbo

    references to the geographical location of Rakhine State

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Collider
    -0.79
    apsed
    -0.70
     Replay
    -0.68
    ACTED
    -0.67
     Reaper
    -0.66
     Harm
    -0.66
    Jane
    -0.66
     Polo
    -0.65
    POS
    -0.65
     Vox
    -0.64
    POSITIVE LOGITS
    akh
    1.38
    urst
    1.23
    stan
    1.04
    azard
    0.99
    ritis
    0.95
    icter
    0.95
    achev
    0.95
    arov
    0.93
    iak
    0.92
    withstanding
    0.92
    Activations Density 0.007%

    No Known Activations