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. 11-RES-JB
    6. 2961
    Prev
    Next
    INDEX
    Explanations

    words related to birds

    oai_token-act-pair · gpt-3.5-turbo

    references and mentions of birds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Toro
    -0.69
    FINE
    -0.69
    gp
    -0.67
     Uzbek
    -0.65
     gp
    -0.62
     DPR
    -0.62
    RED
    -0.60
    ushima
    -0.60
     Applicant
    -0.59
    imaru
    -0.58
    POSITIVE LOGITS
    seed
    1.26
    watching
    1.10
    wat
    1.03
    hawk
    1.00
    bird
    0.98
     nesting
    0.92
    species
    0.92
    birds
    0.91
     nests
    0.90
    feed
    0.90
    Activations Density 0.045%

    No Known Activations