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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 10821
    Prev
    Next
    INDEX
    Explanations

    names like "Boo" and terms related to boilers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and corporate entities, particularly those with the name "Boo" or related to "Carly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igators
    -0.87
    代
    -0.86
    olution
    -0.81
    pite
    -0.80
    igator
    -0.78
    guide
    -0.78
    ional
    -0.75
    ç¥ŀ
    -0.74
    idency
    -0.72
    olars
    -0.70
    POSITIVE LOGITS
     Boo
    1.22
    Boo
    1.08
    leans
    1.08
    gey
    0.98
    zing
    0.95
    lean
    0.90
    etooth
    0.87
    veland
    0.84
    zman
    0.83
    vernment
    0.83
    Activations Density 0.006%

    No Known Activations