© 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. 20161
    Prev
    Next
    INDEX
    Explanations

    words related to legal appeals

    oai_token-act-pair · gpt-3.5-turbo

    references to legal appeals

    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
    rats
    -0.68
    walker
    -0.66
    leted
    -0.65
     Sigma
    -0.64
    leep
    -0.63
    Spoiler
    -0.62
    rake
    -0.62
    ress
    -0.59
     contracted
    -0.58
     Chimera
    -0.58
    POSITIVE LOGITS
     appeals
    3.94
     appeal
    2.49
     Appeals
    2.23
     appealed
    2.22
     Appeal
    2.06
     appellate
    1.75
     appealing
    1.66
     pleas
    1.35
    eals
    1.28
     plea
    1.23
    Activations Density 0.010%

    No Known Activations