Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20327
    Prev
    Next
    INDEX
    Explanations

    mentions or references to technology or electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    references to technology and technological terms

    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
    âĸijâĸij
    -0.68
    Factor
    -0.62
    DATA
    -0.60
     slam
    -0.59
     breeze
    -0.59
    æĿ
    -0.59
     Suz
    -0.56
    ģ
    -0.55
     Swanson
    -0.55
     sail
    -0.54
    POSITIVE LOGITS
    phe
    1.24
    ipop
    1.23
    ounge
    1.20
    ateral
    1.20
    onial
    1.16
    ibrary
    1.13
    ivia
    1.10
    ocation
    1.09
    anguages
    1.08
    ocated
    1.06
    Activations Density 0.045%

    No Known Activations