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. 10-RES-JB
    6. 22326
    Prev
    Next
    INDEX
    Explanations

    economic and statistical figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ²¾
    -0.65
    hai
    -0.62
    obbies
    -0.58
    ardi
    -0.57
    ocent
    -0.57
    hid
    -0.57
     Blog
    -0.57
    ochemical
    -0.56
     Franch
    -0.55
    trust
    -0.55
    POSITIVE LOGITS
     surpass
    0.99
     exceeding
    0.99
     equivalent
    0.92
     eclips
    0.92
     surpassed
    0.91
    phabet
    0.87
    highest
    0.85
     exceeds
    0.84
     topping
    0.83
     fraction
    0.82
    Activations Density 0.220%

    No Known Activations