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. 11018
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and software products

    oai_token-act-pair · gpt-3.5-turbo

    references to specific models or types of products, particularly electronics or tech

    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
    getic
    -0.63
     behavi
    -0.63
    kson
    -0.62
     beh
    -0.62
     smelling
    -0.62
     Somew
    -0.61
     compartment
    -0.60
    Ú
    -0.60
    Ø©
    -0.59
     TODAY
    -0.58
    POSITIVE LOGITS
    avier
    1.39
    peria
    1.30
    III
    1.25
    VII
    1.25
    cellence
    1.14
    IX
    1.12
    II
    1.06
    VI
    1.02
    posed
    1.02
    ML
    1.01
    Activations Density 0.055%

    No Known Activations