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. 3-RES-JB
    6. 2662
    Prev
    Next
    INDEX
    Explanations

    adjectives related to physical injuries or emotional distress

    oai_token-act-pair · gpt-3.5-turbo

    words associated with trauma and damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.78
    orr
    -0.75
    perty
    -0.72
    icipated
    -0.72
    hum
    -0.70
     COURT
    -0.69
    quickShipAvailable
    -0.68
    ographers
    -0.68
    ARA
    -0.67
    è£ħ
    -0.67
    POSITIVE LOGITS
    ness
    0.92
    nesses
    0.84
     aback
    0.83
    adoes
    0.81
     Nadu
    0.72
    rive
    0.70
    river
    0.70
     Panda
    0.69
    gling
    0.67
     wast
    0.63
    Activations Density 0.104%

    No Known Activations