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. 3-RES-JB
    6. 7399
    Prev
    Next
    INDEX
    Explanations

    references to various types of advocacy and community groups

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of social and political groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Delivery
    -0.70
    cffffcc
    -0.70
    ãĤ¨ãĥ«
    -0.68
    Rah
    -0.65
    wards
    -0.63
     Mansion
    -0.63
    à¥
    -0.63
     Meridian
    -0.63
     Hus
    -0.62
    âĺħâĺħ
    -0.62
    POSITIVE LOGITS
    etter
    1.12
    hips
    1.00
    etting
    0.99
    ongs
    0.97
    wana
    0.96
    ourcing
    0.94
     groups
    0.93
    hell
    0.92
    aurus
    0.90
    chool
    0.90
    Activations Density 0.049%

    No Known Activations