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. 11-RES-JB
    6. 15220
    Prev
    Next
    INDEX
    Explanations

    information related to technical specifications, discounts, and pricing

    oai_token-act-pair · gpt-3.5-turbo

    financial terms and conditions related to pricing and shipping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.65
    wikipedia
    -0.65
    anners
    -0.62
    theless
    -0.62
    pedia
    -0.60
    çIJ
    -0.59
    Anyway
    -0.59
     Wikimedia
    -0.58
    Years
    -0.58
    selves
    -0.57
    POSITIVE LOGITS
     TBD
    0.61
     max
    0.58
     block
    0.54
    ific
    0.53
    ]+
    0.52
     default
    0.52
     valid
    0.51
     10
    0.51
    10
    0.51
    el
    0.51
    Activations Density 0.364%

    No Known Activations