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. 11-RES-JB
    6. 8671
    Prev
    Next
    INDEX
    Explanations

    phrases and keywords related to the word "blow"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Bl" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yankee
    -0.67
    lessly
    -0.65
     industrial
    -0.63
     yeast
    -0.62
     Bulldogs
    -0.60
     dare
    -0.59
     controlling
    -0.59
     generals
    -0.59
     SYSTEM
    -0.59
     artificially
    -0.58
    POSITIVE LOGITS
    ossom
    1.43
    acks
    1.40
    izzard
    1.35
    adder
    1.34
    anca
    1.30
    ooming
    1.30
    ocking
    1.30
    ocked
    1.30
    ues
    1.29
    anco
    1.26
    Activations Density 0.019%

    No Known Activations