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. 10-RES-JB
    6. 19851
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    specific keywords or names associated with events or individuals in sports-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ×Ļ
    -0.66
    Americ
    -0.65
     Parables
    -0.63
    Ñı
    -0.63
    ãĥĸ
    -0.62
    onies
    -0.59
    ×Ļ×
    -0.58
    orate
    -0.58
    ר
    -0.57
    ORK
    -0.56
    POSITIVE LOGITS
    's
    0.92
     himself
    0.86
     complied
    0.73
    theless
    0.73
     adjusts
    0.72
     enjoys
    0.72
    dinand
    0.71
     Labs
    0.70
     herself
    0.70
     realizes
    0.70
    Activations Density 0.204%

    No Known Activations