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. 11-RES-JB
    6. 18124
    Prev
    Next
    INDEX
    Explanations

    names of people or organizations formatted in a specific way (\<Name\> /AP \<Name\> /\)

    oai_token-act-pair · gpt-3.5-turbo

    aspects related to media and formal documentation

    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
    stal
    -0.88
    Lewis
    -0.86
     Lewis
    -0.86
     Bel
    -0.82
     Lyme
    -0.82
    \\\\\\\\\\\\\\\\
    -0.81
    lie
    -0.74
    iously
    -0.74
     Yel
    -0.73
     Elijah
    -0.73
    POSITIVE LOGITS
     AP
    2.05
    AP
    2.05
    ap
    1.82
    APS
    1.68
     Ap
    1.59
     SAP
    1.55
     Pap
    1.51
    Ap
    1.50
     ap
    1.48
     Sap
    1.40
    Activations Density 0.323%

    No Known Activations