© 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. 3-RES-JB
    6. 23180
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions or legal processes

    oai_token-act-pair · gpt-3.5-turbo

    references to legal actions or cases involving prosecution

    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
    olen
    -0.72
    iba
    -0.71
     nutrit
    -0.70
     regener
    -0.65
     hypers
    -0.63
     Columb
    -0.63
    kell
    -0.62
     Pixie
    -0.61
     livest
    -0.61
     saline
    -0.61
    POSITIVE LOGITS
    eering
    1.09
     prosecution
    0.98
     prosecuted
    0.88
     prosecute
    0.82
    secution
    0.79
     alleges
    0.76
     Hearing
    0.76
    alties
    0.74
     investigator
    0.74
     proceedings
    0.73
    Activations Density 0.025%

    No Known Activations