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. 10-RES-JB
    6. 1627
    Prev
    Next
    INDEX
    Explanations

    words related to authority, like "bridge" in the context of crossing a line, or "violence" in the context of exerting power

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to structured data, conditions, and entities relevant to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     condem
    -0.58
     Tro
    -0.58
     IPM
    -0.58
     ts
    -0.57
     df
    -0.56
     Tray
    -0.55
     Pry
    -0.55
    dden
    -0.53
     Qué
    -0.53
    dx
    -0.53
    POSITIVE LOGITS
     alone
    0.88
    ativity
    0.73
    ģĸ
    0.69
     haun
    0.68
    â̲
    0.63
    alien
    0.62
     INCLUD
    0.61
    lando
    0.61
     expired
    0.60
     disappeared
    0.59
    Activations Density 0.264%

    No Known Activations