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. 14977
    Prev
    Next
    INDEX
    Explanations

    items or objects that can be used for practical or everyday purposes

    oai_token-act-pair · gpt-3.5-turbo

    items or objects that can be used in various contexts or activities

    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
     experien
    -0.64
    ocracy
    -0.62
     realm
    -0.62
     partnership
    -0.61
     Response
    -0.61
    scape
    -0.61
     circumstance
    -0.60
    eworld
    -0.60
    uve
    -0.60
    abama
    -0.60
    POSITIVE LOGITS
    poons
    1.36
     stuffed
    1.10
     coated
    1.07
     fashioned
    1.04
    mith
    1.04
     adorned
    1.03
    uits
    1.03
     laced
    1.03
     containing
    1.03
    avers
    0.98
    Activations Density 0.366%

    No Known Activations