© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 24170
    Prev
    Next
    INDEX
    Explanations

    names of people and terms related to legal issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms indicating concepts of legality or regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     convergence
    -0.76
    anium
    -0.74
     comprom
    -0.72
     mathemat
    -0.68
     carbohyd
    -0.66
    schild
    -0.63
    raints
    -0.63
     Gutenberg
    -0.62
     XT
    -0.62
    enegger
    -0.62
    POSITIVE LOGITS
    Ļ
    0.96
    ļ
    0.84
    maid
    0.84
    İ
    0.81
    ħ
    0.80
    ĩ
    0.77
    ı
    0.75
    ij
    0.74
    ł
    0.74
    ķ
    0.73
    Activations Density 0.362%

    No Known Activations