© 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. 3-RES-JB
    11. 15237
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Bhutan

    oai_token-act-pair · gpt-3.5-turbo

    references to Bhutan

    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
    PORT
    -0.82
    eers
    -0.81
    swick
    -0.74
     Wolves
    -0.71
    furt
    -0.70
    BALL
    -0.68
    geist
    -0.68
    phis
    -0.67
    */(
    -0.67
    FOX
    -0.66
    POSITIVE LOGITS
    aji
    1.10
    awan
    1.04
    omes
    1.00
    orns
    0.99
    enn
    0.98
     Bh
    0.98
    reath
    0.97
    utan
    0.92
    ahah
    0.91
    ongs
    0.90
    Activations Density 0.009%

    No Known Activations