© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 24549
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Bhutan

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Bhutan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.77
     Marse
    -0.69
    eering
    -0.64
     sto
    -0.62
     Grizzlies
    -0.62
     Revelations
    -0.61
    PORT
    -0.61
     FANTASY
    -0.60
     ROCK
    -0.60
     recess
    -0.59
    POSITIVE LOGITS
    utan
    1.08
    azard
    1.08
    awan
    1.08
    arta
    1.07
    aji
    1.05
    omes
    1.03
    ikk
    1.03
    ospital
    1.02
    agy
    1.01
    izoph
    1.01
    Activations Density 0.023%

    No Known Activations