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. 19119
    Prev
    Next
    INDEX
    Explanations

    references to entities or companies named "Gaz" and medical terms referring to medicines or healthcare facilities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations and organizations related to the Gaza region

    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
    avorite
    -0.78
     erosion
    -0.63
    nington
    -0.62
    course
    -0.61
    hander
    -0.61
     plaque
    -0.61
    plan
    -0.61
     tongue
    -0.60
    pattern
    -0.59
    dding
    -0.59
    POSITIVE LOGITS
    ians
    1.52
    inals
    1.31
    inal
    1.30
    ially
    1.20
    iated
    1.20
    iation
    1.14
    ian
    1.14
    iate
    1.13
    ine
    1.09
    iations
    1.08
    Activations Density 0.061%

    No Known Activations