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. 6725
    Prev
    Next
    INDEX
    Explanations

    words related to names, particularly last names

    oai_token-act-pair · gpt-3.5-turbo

    words related to individuals with the surname "ini."

    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
    ¥µ
    -0.86
    spin
    -0.75
    é¾įå¥ij士
    -0.74
    ĻĤ
    -0.71
    saw
    -0.70
    lished
    -0.69
    friends
    -0.68
    names
    -0.68
    Ĥ¬
    -0.67
    deck
    -0.67
    POSITIVE LOGITS
    zzle
    1.01
    ini
    0.94
    emi
    0.91
    zzo
    0.91
    Äĩ
    0.88
    zzi
    0.87
    opsis
    0.87
    otti
    0.87
     Rossi
    0.86
    ÃŁ
    0.84
    Activations Density 0.010%

    No Known Activations