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. 1-RES-JB
    6. 18162
    Prev
    Next
    INDEX
    Explanations

    weights in kilograms

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measures of weight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gotten
    -0.74
    bidden
    -0.70
    protected
    -0.66
    western
    -0.66
    vice
    -0.66
    Ire
    -0.66
    href
    -0.65
    structed
    -0.65
    bes
    -0.62
     Dee
    -0.62
    POSITIVE LOGITS
    kg
    1.10
     kg
    1.01
    atsu
    0.83
    enger
    0.82
     kilograms
    0.80
    cup
    0.78
     ammonia
    0.77
    JV
    0.77
    ingly
    0.76
    vl
    0.75
    Activations Density 0.005%

    No Known Activations