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. 20511
    Prev
    Next
    INDEX
    Explanations

    instances involving the action of pulling or extracting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pull" in various contexts

    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
    ibel
    -0.84
    esan
    -0.78
    merce
    -0.78
    voy
    -0.78
    brates
    -0.75
    afort
    -0.74
    esa
    -0.73
    SPONSORED
    -0.72
    apolis
    -0.71
    brate
    -0.70
    POSITIVE LOGITS
    pull
    1.01
     aggro
    0.96
     levers
    0.96
     pull
    0.95
    Pull
    0.91
     sled
    0.81
    chairs
    0.80
     weeds
    0.77
    quote
    0.73
     carts
    0.73
    Activations Density 0.023%

    No Known Activations