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. 2-RES-JB
    6. 22821
    Prev
    Next
    INDEX
    Explanations

    letters that are put together like 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or metrics related to counts or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.96
    ername
    -0.94
    iage
    -0.78
    terday
    -0.75
     oun
    -0.74
    terness
    -0.74
    uto
    -0.73
    hement
    -0.73
    lihood
    -0.70
    agy
    -0.66
    POSITIVE LOGITS
    Mand
    0.85
    Quotes
    0.79
    LESS
    0.78
    WIND
    0.78
    Viol
    0.77
    Trivia
    0.76
    Cla
    0.76
    OVER
    0.76
    Act
    0.75
    ORN
    0.74
    Activations Density 0.499%

    No Known Activations