© 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. 7826
    Prev
    Next
    INDEX
    Explanations

    emails with information about subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription and receiving updates or newsletters

    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
    iaries
    -0.70
    livious
    -0.68
    imer
    -0.67
     Catalyst
    -0.67
    asers
    -0.64
    ono
    -0.64
    aimon
    -0.63
    chio
    -0.60
    imester
    -0.59
    hee
    -0.58
    POSITIVE LOGITS
    interstitial
    0.87
    $$$$
    0.75
     });
    0.67
    ]);
    0.63
    大
    0.62
    ]=
    0.61
    ]+
    0.60
     privileges
    0.58
    ").
    0.58
     unlocks
    0.58
    Activations Density 0.037%

    No Known Activations