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. 10773
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of importance, value, and significance

    oai_token-act-pair · gpt-3.5-turbo

    key concepts and values related to needs and their impacts

    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
    Had
    -0.69
     Had
    -0.61
    were
    -0.59
     Said
    -0.59
    aughed
    -0.58
    sed
    -0.57
    iped
    -0.57
    addon
    -0.56
    arij
    -0.54
    Were
    -0.54
    POSITIVE LOGITS
     depends
    1.45
     tends
    1.41
     determines
    1.37
     requires
    1.35
     varies
    1.35
     is
    1.34
     becomes
    1.34
     isn
    1.29
     can
    1.29
     involves
    1.26
    Activations Density 0.889%

    No Known Activations