© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4824
    Prev
    Next
    INDEX
    Explanations

    specific legal terms and sentences related to court cases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms and phrases related to legal sentencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Proxy
    -0.82
     Secrets
    -0.73
    amera
    -0.73
    akery
    -0.73
     nests
    -0.71
    ijn
    -0.71
    kas
    -0.70
    nect
    -0.69
    KEY
    -0.68
    sels
    -0.68
    POSITIVE LOGITS
     sentences
    1.42
     sentencing
    1.40
     sentence
    1.39
     harsher
    1.34
     punishments
    1.31
     punishment
    1.31
     imposed
    1.27
     hars
    1.23
     len
    1.15
     sentenced
    1.11
    Activations Density 0.224%

    No Known Activations