Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 12893
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology related to appeals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal appeals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fters
    -0.85
    kson
    -0.82
    estial
    -0.75
    ifa
    -0.74
    mson
    -0.70
     Benz
    -0.69
    obyl
    -0.65
     Coh
    -0.64
    ipes
    -0.64
    avery
    -0.63
    POSITIVE LOGITS
     parole
    0.75
     pend
    0.74
     denial
    0.71
     tribunal
    0.70
     rejection
    0.70
    ĸļ
    0.69
     appeals
    0.69
     judge
    0.68
    DEN
    0.68
     judicial
    0.67
    Activations Density 0.019%

    No Known Activations