Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 4187
    Prev
    Next
    INDEX
    Explanations

    references to a particular sports team, possibly related to soccer based on terms like "Arsenal" and "Gunners"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Gun."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç«
    -0.77
    åĬ
    -0.73
    Reviewed
    -0.73
     Ethiop
    -0.71
     Sina
    -0.71
     Archdemon
    -0.69
     DOE
    -0.67
    ATURE
    -0.64
    Sax
    -0.63
     Yose
    -0.62
    POSITIVE LOGITS
    powder
    1.13
    gun
    1.10
    Gun
    1.08
    ners
    1.07
    smith
    1.04
    nery
    1.04
    nar
    1.04
    guns
    1.04
    ner
    1.03
    boats
    0.99
    Activations Density 0.009%

    No Known Activations