© 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. 14894
    Prev
    Next
    INDEX
    Explanations

    terms related to political candidates, legal issues, and potential threats or challenges

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political contexts, particularly concerning candidates, legal implications, and military issues

    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
    istered
    -0.65
    ĸļ
    -0.63
     Disabled
    -0.62
    oxide
    -0.60
    Bench
    -0.60
     sadly
    -0.59
     Mahjong
    -0.59
    inately
    -0.58
    entimes
    -0.58
    yss
    -0.58
    POSITIVE LOGITS
    rosso
    0.77
    worthiness
    0.75
    comings
    0.74
     scenarios
    0.73
    zzle
    0.72
    arenthood
    0.72
     sqor
    0.72
     liabilities
    0.71
    ãĥĥãĥĪ
    0.68
     outl
    0.65
    Activations Density 0.358%

    No Known Activations