© 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. 8-RES-JB
    11. 495
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    empty or non-informative sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    herer
    -0.65
    *.
    -0.60
     accordingly
    -0.59
     beforehand
    -0.59
    ornings
    -0.58
     afterwards
    -0.56
    /"
    -0.56
    entimes
    -0.56
    aria
    -0.55
     alongside
    -0.54
    POSITIVE LOGITS
     foregoing
    0.74
    oret
    0.74
    resa
    0.74
     same
    0.74
    ses
    0.74
     simplest
    0.73
     smallest
    0.72
     Clintons
    0.71
     remainder
    0.70
     hottest
    0.70
    Activations Density 0.840%

    No Known Activations