Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17830
    Prev
    Next
    INDEX
    Explanations

    adjectives describing intensity or strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    the word "fierce" and its variants, indicating intensity or severity

    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
     Album
    -0.71
     Processing
    -0.69
     Misc
    -0.69
     Option
    -0.68
     Transactions
    -0.67
     Episode
    -0.66
    BD
    -0.66
    gram
    -0.65
    iture
    -0.65
    Ped
    -0.64
    POSITIVE LOGITS
     fierce
    3.39
     ferocious
    2.32
     fiercely
    2.02
     vehement
    1.58
     fearsome
    1.58
     formidable
    1.57
     fiery
    1.52
     ruthless
    1.50
     relentless
    1.44
     spirited
    1.43
    Activations Density 0.017%

    No Known Activations