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. 6-RES-JB
    6. 21366
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to Washington D.C., specifically referencing the C.9. region

    oai_token-act-pair · gpt-3.5-turbo

    references to the District of Columbia (D.C.)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Maker
    -0.95
    ãĥĦ
    -0.78
    ãĥĨãĤ£
    -0.77
    ãĤ¯
    -0.77
    ãĥŀ
    -0.75
    Materials
    -0.71
    ãĥĭ
    -0.70
    Filename
    -0.66
    ãĥĹ
    -0.66
    ãĥĻ
    -0.65
    POSITIVE LOGITS
    .,
    0.86
    rawl
    0.84
    itation
    0.79
    ruck
    0.78
    upid
    0.78
    ember
    0.75
    adel
    0.75
    airo
    0.74
    elsius
    0.74
    urry
    0.73
    Activations Density 0.020%

    No Known Activations