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. 6-RES-JB
    6. 11091
    Prev
    Next
    INDEX
    Explanations

    ingredients or items related to pepper, specifically pepper spray

    oai_token-act-pair · gpt-3.5-turbo

    references to "pepper" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hematic
    -0.84
    ADRA
    -0.82
    ģĸ
    -0.73
     EntityItem
    -0.73
    LD
    -0.70
    rians
    -0.69
    UE
    -0.67
    ItemTracker
    -0.67
     Objective
    -0.67
    ndum
    -0.66
    POSITIVE LOGITS
    mint
    1.51
     pepper
    0.99
     peppers
    0.92
     flakes
    0.87
     spray
    0.86
    nic
    0.83
    iously
    0.83
    ious
    0.81
    icum
    0.81
    ient
    0.81
    Activations Density 0.023%

    No Known Activations