© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 1814
    Prev
    Next
    INDEX
    Explanations

    legal terms such as 'acquitted', 'exonerated', and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal acquittals and exonerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hop
    -0.74
    OPER
    -0.72
    emetery
    -0.68
    DAY
    -0.67
    BD
    -0.66
    GER
    -0.64
    KEY
    -0.64
    ummer
    -0.62
    pite
    -0.61
    hall
    -0.61
    POSITIVE LOGITS
     acquitted
    1.15
     exoner
    0.92
    ittal
    0.84
     indict
    0.81
     verdict
    0.79
    lect
    0.78
     indicted
    0.73
     immunity
    0.72
    Ń·
    0.72
    wright
    0.71
    Activations Density 0.013%

    No Known Activations