© 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. 2-RES-JB
    11. 9218
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'alcohol' at varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to alcohol and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arity
    -0.75
    Dear
    -0.70
     Telecom
    -0.70
     Dear
    -0.69
     Kaw
    -0.68
     Postal
    -0.67
     NCT
    -0.66
    VIEW
    -0.66
     Pon
    -0.66
     Goff
    -0.64
    POSITIVE LOGITS
     alcohol
    1.18
    cohol
    1.14
     beverages
    1.06
     drinkers
    1.04
    alcohol
    1.04
    ocaust
    1.03
     beverage
    1.02
     dehyd
    0.99
     liquor
    0.98
     poisoning
    0.96
    Activations Density 0.010%

    No Known Activations