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. 0-RES-JB
    6. 21430
    Prev
    Next
    INDEX
    Explanations

    phrases related to power dynamics and moral responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references or mentions of the concept of freedom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iPod
    -0.65
     Henri
    -0.61
     lay
    -0.61
     Continental
    -0.61
     Dele
    -0.60
     email
    -0.60
     Crom
    -0.57
     Proud
    -0.57
     mandate
    -0.57
     Carrier
    -0.57
    POSITIVE LOGITS
    Ŀ
    4.29
    Ł
    1.81
    ľ
    1.80
    ¡
    1.76
    ļ
    1.73
    ª
    1.65
    ©
    1.65
    ĺ
    1.65
    Ĺ
    1.61
    ŀ
    1.61
    Activations Density 0.267%

    No Known Activations