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. 15655
    Prev
    Next
    INDEX
    Explanations

    particular phrases representing meeting certain standards or requirements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to meeting criteria or standards

    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
    artifacts
    -0.71
    apsed
    -0.67
    hander
    -0.63
     Oops
    -0.63
    cloth
    -0.62
    irez
    -0.61
    achus
    -0.59
    ochet
    -0.59
     headquartered
    -0.58
    coins
    -0.58
    POSITIVE LOGITS
     criteria
    1.65
     requirements
    1.60
     expectations
    1.34
     specifications
    1.34
     standards
    1.32
     criterion
    1.31
     deadlines
    1.30
     quotas
    1.28
     benchmarks
    1.26
     thresholds
    1.23
    Activations Density 0.147%

    No Known Activations