© 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. 4-RES-JB
    11. 15681
    Prev
    Next
    INDEX
    Explanations

    references to legal exoneration, particularly with mention of Rudy Giuliani

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exoneration and notable figures associated with legal issues

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

    No Comments

    Negative Logits
    ombat
    -0.87
    itals
    -0.87
    aic
    -0.84
    birth
    -0.82
    xual
    -0.80
    locks
    -0.79
    icult
    -0.75
    ipeg
    -0.75
    held
    -0.75
    stead
    -0.74
    POSITIVE LOGITS
     Giuliani
    1.26
     Rudy
    0.87
    senal
    0.80
     CTR
    0.78
    agate
    0.74
     Serie
    0.72
    ATES
    0.72
     scapego
    0.72
     Cosponsors
    0.70
     CSI
    0.67
    Activations Density 0.032%

    No Known Activations