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. 0-RES-JB
    6. 8872
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and file types

    oai_token-act-pair · gpt-3.5-turbo

    references to software extensions

    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
     Rural
    -0.73
    estine
    -0.73
     fight
    -0.71
     mentality
    -0.71
     situation
    -0.67
    itamin
    -0.67
     Narr
    -0.65
    ewater
    -0.65
     scene
    -0.65
     Institution
    -0.64
    POSITIVE LOGITS
     extensions
    3.51
     Extensions
    2.85
     additions
    1.46
     enhancements
    1.41
     expansions
    1.40
     modifications
    1.31
     attachments
    1.30
     replacements
    1.26
     plugins
    1.25
     exceptions
    1.25
    Activations Density 0.019%

    No Known Activations