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. 11831
    Prev
    Next
    INDEX
    Explanations

    verbs related to visual perception

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to visual perception or observation

    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
    theless
    -0.68
    tele
    -0.59
    ads
    -0.58
    economic
    -0.58
    trap
    -0.57
    ilts
    -0.57
    orously
    -0.56
    RET
    -0.56
    aments
    -0.56
    ament
    -0.55
    POSITIVE LOGITS
     unfold
    1.08
     happening
    0.99
     happen
    0.98
     firsthand
    0.93
     unfolding
    0.92
     occurring
    0.80
     fit
    0.79
    aturday
    0.79
     emanating
    0.77
     occur
    0.74
    Activations Density 0.056%

    No Known Activations