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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5356
    Prev
    Next
    INDEX
    Explanations

    words related to legal or medical issues

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various cases, particularly in medical or legal contexts

    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
    mire
    -0.66
    rift
    -0.66
     Submission
    -0.63
    liv
    -0.63
     Amen
    -0.62
     Publisher
    -0.61
     grin
    -0.61
    AAAA
    -0.60
    song
    -0.59
    SPONSORED
    -0.58
    POSITIVE LOGITS
     cases
    3.75
     Cases
    3.14
    cases
    2.72
     case
    2.44
     instances
    2.11
    case
    1.96
    Case
    1.94
     prosecutions
    1.90
     Case
    1.89
     situations
    1.69
    Activations Density 0.018%

    No Known Activations