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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 13112
    Prev
    Next
    INDEX
    Explanations

    verbs related to flowing or movement, specifically the action of pouring

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nton
    -0.66
    locked
    -0.65
     Nanto
    -0.64
    nesota
    -0.64
    abiding
    -0.63
    ften
    -0.62
    ansas
    -0.61
    otics
    -0.61
    tarians
    -0.61
    ALE
    -0.61
    POSITIVE LOGITS
     encour
    1.44
     scorn
    0.89
     poured
    0.89
     boiling
    0.86
     buckets
    0.81
     pouring
    0.80
    pour
    0.79
     forth
    0.77
     gallons
    0.77
     litres
    0.76
    Activations Density 0.045%

    No Known Activations