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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 4342
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and references to court proceedings

    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
    allo
    -0.66
     Recomm
    -0.66
    ahime
    -0.65
    ologically
    -0.62
    illary
    -0.61
     reeling
    -0.60
    oslov
    -0.59
     embr
    -0.58
    kat
    -0.57
    alach
    -0.56
    POSITIVE LOGITS
    ignment
    1.02
    ignty
    0.91
    ignt
    0.81
    igned
    0.79
    ipation
    0.79
    ctions
    0.79
    ign
    0.75
    owers
    0.74
    asks
    0.74
    jury
    0.72
    Activations Density 0.084%

    No Known Activations