© 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. 9-RES-JB
    11. 9951
    Prev
    Next
    INDEX
    Explanations

    verbs related to pouring or acts of pouring liquid or substances

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pour" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.70
     Finder
    -0.69
     Cosponsors
    -0.66
    ansas
    -0.65
     Nanto
    -0.65
    ALE
    -0.61
     Recall
    -0.61
     Named
    -0.61
    sein
    -0.60
    usable
    -0.60
    POSITIVE LOGITS
     encour
    1.37
     scorn
    0.97
     boiling
    0.92
     poured
    0.86
     forth
    0.85
     gallons
    0.84
     molten
    0.84
     bleach
    0.81
     buckets
    0.80
     into
    0.80
    Activations Density 0.067%

    No Known Activations