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. 7-RES-JB
    6. 20290
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Bamb."

    oai_token-act-pair · gpt-3.5-turbo

    words and patterns related to the concept of "megabytes" (mb)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coni
    -0.70
    ources
    -0.64
    meal
    -0.63
    aways
    -0.62
     mosaic
    -0.61
     è£ı
    -0.60
    ãĥīãĥ©ãĤ´ãĥ³
    -0.60
    come
    -0.60
    zona
    -0.60
    GROUND
    -0.59
    POSITIVE LOGITS
    iotic
    1.06
    uild
    1.00
    iosis
    0.95
    edded
    0.92
    iotics
    0.91
    athy
    0.86
    ortal
    0.86
    ole
    0.86
    assy
    0.86
    iscopal
    0.85
    Activations Density 0.020%

    No Known Activations