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. 10968
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific individual named "Bastian."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a particular name or term related to a person or character

    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
    skirts
    -0.83
    PLIED
    -0.75
    ãģ¦
    -0.73
    ãĤĭ
    -0.68
    ×Ļ×
    -0.68
    protein
    -0.66
    ethnic
    -0.65
    early
    -0.64
    POR
    -0.64
    FACE
    -0.63
    POSITIVE LOGITS
     Bast
    1.07
    illus
    0.96
    ille
    0.92
    illes
    0.88
    ards
    0.85
    halla
    0.82
    illo
    0.82
    aur
    0.80
    illon
    0.80
    alo
    0.78
    Activations Density 0.007%

    No Known Activations