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. 10-RES-JB
    6. 15096
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions involving pulling something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verbs "pull" and "pulled."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.90
    afort
    -0.83
    xus
    -0.75
    mble
    -0.75
     ILCS
    -0.74
    mint
    -0.73
     cannabin
    -0.73
    SPONSORED
    -0.70
     Fallen
    -0.70
    igmatic
    -0.69
    POSITIVE LOGITS
    pull
    1.00
    quote
    0.95
     levers
    0.95
    overs
    0.88
     aggro
    0.88
    down
    0.86
    imentary
    0.86
    Pull
    0.81
     Quote
    0.81
     trigger
    0.81
    Activations Density 0.022%

    No Known Activations