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. 8-RES-JB
    6. 1425
    Prev
    Next
    INDEX
    Explanations

    words related to names or proper nouns, specifically those starting with "Lar" or "Lor"

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to individuals, likely focusing on the name "Lar" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®éŃĶ
    -0.93
    CRIP
    -0.91
    EEK
    -0.80
    士
    -0.74
    ELS
    -0.73
    éĹĺ
    -0.73
    代
    -0.73
    ARDS
    -0.67
    HI
    -0.67
    ħĭ
    -0.66
    POSITIVE LOGITS
    rigan
    1.06
    abee
    0.97
    issa
    0.94
    vae
    0.93
    amar
    0.91
    opa
    0.91
    imer
    0.89
    azon
    0.89
    thur
    0.89
    ousse
    0.88
    Activations Density 0.027%

    No Known Activations