© 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. 4-RES-JB
    11. 10532
    Prev
    Next
    INDEX
    Explanations

    keywords related to the geographical location "Mindanao."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Mindanao"

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

    No Comments

    Negative Logits
    DIR
    -0.76
    ARDS
    -0.73
     Mehran
    -0.73
    thumbnails
    -0.71
    ARD
    -0.70
    ATED
    -0.68
     audible
    -0.67
    EStreamFrame
    -0.67
    VEL
    -0.67
     sever
    -0.65
    POSITIVE LOGITS
    fulness
    1.27
    ful
    1.08
    bender
    0.99
    iac
    0.94
    mind
    0.93
    piece
    0.89
    storms
    0.88
    scape
    0.86
    less
    0.86
    Mind
    0.86
    Activations Density 0.012%

    No Known Activations