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. 5596
    Prev
    Next
    INDEX
    Explanations

    words related to a specific language or country, particularly with special characters like 'ç'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "chach" or similar variations

    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
     scaven
    -0.70
     Utility
    -0.66
     Apocalypse
    -0.61
     Reaper
    -0.61
     stealing
    -0.60
     killing
    -0.60
     chores
    -0.60
     Keeper
    -0.60
     poisons
    -0.59
     destroyer
    -0.58
    POSITIVE LOGITS
    ç
    4.90
    ça
    2.65
    ÅŁ
    2.04
    ÄŁ
    1.83
    Äį
    1.45
    ã
    1.43
    ão
    1.42
    Å¡
    1.42
    Äĩ
    1.41
    ê
    1.40
    Activations Density 0.010%

    No Known Activations