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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 3314
    Prev
    Next
    INDEX
    Explanations

    mentions of the Dalai Lama

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Dalai Lama and related activities

    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
    afort
    -0.89
    alach
    -0.81
    acement
    -0.74
    ipop
    -0.72
    heny
    -0.70
    heric
    -0.70
    apor
    -0.70
    ioned
    -0.69
    sburgh
    -0.69
    agra
    -0.68
    POSITIVE LOGITS
    ãĥ³ãĤ¸
    1.06
    ãĥĥãĤ¯
    0.86
    çľ
    0.83
    rients
    0.81
    ç·
    0.80
    jiang
    0.80
    ÄŁ
    0.73
     Haram
    0.72
    itialized
    0.72
    stad
    0.70
    Activations Density 0.014%

    No Known Activations