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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 17365
    Prev
    Next
    INDEX
    Explanations

    actions related to physical movements or gestures

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate giving or moving towards something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.70
     vows
    -0.65
     boycot
    -0.64
     warr
    -0.60
     drafted
    -0.59
     trusts
    -0.59
     warrants
    -0.58
    owship
    -0.58
     Monthly
    -0.58
     advertis
    -0.57
    POSITIVE LOGITS
    ggles
    1.15
     stabilize
    1.11
     minimize
    1.09
    wered
    1.07
     relieve
    1.07
     ensure
    1.06
     maximize
    1.06
    othy
    1.03
     prevent
    1.02
     conserve
    1.02
    Activations Density 0.183%

    No Known Activations