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. 7957
    Prev
    Next
    INDEX
    Explanations

    references to significant life events such as graduations or important announcements

    oai_token-act-pair · gpt-3.5-turbo

    contexts related to significant life events or milestones

    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
     mould
    -0.80
     recognised
    -0.80
     arte
    -0.76
     civilisation
    -0.67
     favoured
    -0.67
     realised
    -0.67
     flavours
    -0.66
     colourful
    -0.66
     aluminium
    -0.66
     authorised
    -0.64
    POSITIVE LOGITS
    âĢ
    1.32
     âĢ
    1.07
    ðŁij
    0.99
    ðŁ
    0.98
    ãĢ
    0.98
    áµ
    0.95
    âľ
    0.94
    ðŁĺ
    0.94
    ï
    0.94
    âϦ
    0.91
    Activations Density 0.961%

    No Known Activations