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. 19647
    Prev
    Next
    INDEX
    Explanations

    words related to legal guilt or confession

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal guilt and pleas

    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
    loc
    -0.67
    Region
    -0.66
     transplant
    -0.62
    ãĤ¡
    -0.62
    ISO
    -0.61
    /+
    -0.61
     extraction
    -0.59
    fly
    -0.59
    к
    -0.58
     Reprodu
    -0.58
    POSITIVE LOGITS
     guilty
    3.86
     Guilty
    2.42
     guilt
    1.71
     culp
    1.55
     complicit
    1.45
     innocent
    1.39
     convicted
    1.35
     criminally
    1.35
     accused
    1.24
     liable
    1.22
    Activations Density 0.023%

    No Known Activations