© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16354
    Prev
    Next
    INDEX
    Explanations

    instances of words related to software functionality

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of functionality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »
    -0.64
    atan
    -0.60
     Baptist
    -0.60
    asin
    -0.60
    igrant
    -0.59
    arie
    -0.58
    cca
    -0.58
    uka
    -0.57
     Foster
    -0.56
    enta
    -0.56
    POSITIVE LOGITS
     functionality
    3.35
     capability
    1.70
     usability
    1.66
     capabilities
    1.63
     functions
    1.62
     function
    1.58
     usefulness
    1.40
     functional
    1.37
     features
    1.36
     compatibility
    1.36
    Activations Density 0.011%

    No Known Activations