© 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. 9-RES-JB
    11. 7597
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and court cases

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terminology and proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĢķ
    -0.71
     --
    -0.65
     depending
    -0.61
     meant
    -0.60
     —
    -0.59
     because
    -0.58
     afterward
    -0.57
     gotten
    -0.56
    —"
    -0.54
     though
    -0.54
    POSITIVE LOGITS
    orkshire
    0.68
    ghai
    0.65
     Honour
    0.65
    thur
    0.63
    culosis
    0.63
    obyl
    0.62
    ndum
    0.62
    osate
    0.61
    isance
    0.60
     cunt
    0.60
    Activations Density 2.087%

    No Known Activations