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. 2-RES-JB
    6. 331
    Prev
    Next
    INDEX
    Explanations

    words that start with the syllable "cra"

    oai_token-act-pair · gpt-4-turbo

    highly activating phrases related to strong desires or cravings

    oai_token-act-pair · gpt-3.5-turbo

    words related to craving or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Democr
    -0.85
    acity
    -0.73
     GOODMAN
    -0.69
    ropolitan
    -0.68
     Hots
    -0.68
     Appropriations
    -0.67
     Annotations
    -0.67
     DPRK
    -0.65
     Sacrament
    -0.65
    itarian
    -0.65
    POSITIVE LOGITS
    igslist
    1.53
    fters
    1.20
    pload
    1.14
    viation
    0.96
     cra
    0.95
    fter
    0.94
    ving
    0.90
    pton
    0.88
    ven
    0.87
    ussia
    0.87
    Activations Density 0.008%

    No Known Activations