Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20864
    Prev
    Next
    INDEX
    Explanations

    legal terms and mentions of legal actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of high-stakes situations or conditions that involve legal or ethical violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.60
    iple
    -0.59
    ety
    -0.55
    ocl
    -0.53
    uber
    -0.51
    cel
    -0.50
    reprene
    -0.48
    odes
    -0.48
    uto
    -0.47
    uit
    -0.47
    POSITIVE LOGITS
     albeit
    1.05
     namely
    1.02
     although
    0.91
     whereas
    0.87
     including
    0.86
     which
    0.82
     though
    0.81
     regardless
    0.77
     but
    0.76
     wherein
    0.76
    Activations Density 0.743%

    No Known Activations