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. 7-RES-JB
    6. 3394
    Prev
    Next
    INDEX
    Explanations

    phrases containing the name "Stella."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Stella."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     citiz
    -0.81
    lon
    -0.79
    ly
    -0.79
    mal
    -0.77
    lied
    -0.74
    nai
    -0.74
    lay
    -0.73
    ulated
    -0.73
    omaly
    -0.72
    ulating
    -0.72
    POSITIVE LOGITS
    ignt
    0.80
    zzo
    0.78
    ppo
    0.78
    opez
    0.76
    ppe
    0.71
    vern
    0.71
     Mara
    0.70
    uder
    0.70
     Fitzgerald
    0.69
    VM
    0.69
    Activations Density 0.058%

    No Known Activations