Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9348
    Prev
    Next
    INDEX
    Explanations

    actions related to consuming alcoholic beverages

    oai_token-act-pair · gpt-3.5-turbo

    activities and social interactions involving drinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elements
    -0.70
     exhibits
    -0.66
     factions
    -0.65
     structures
    -0.65
     organs
    -0.64
     buildings
    -0.64
     entities
    -0.63
     authorities
    -0.62
     districts
    -0.62
     constructs
    -0.62
    POSITIVE LOGITS
    athon
    0.85
    cohol
    0.85
    esome
    0.77
    iversary
    0.77
    phrase
    0.75
    away
    0.75
     shave
    0.75
     apiece
    0.74
    joy
    0.74
     earthqu
    0.71
    Activations Density 0.275%

    No Known Activations