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. 10-RES-JB
    6. 20005
    Prev
    Next
    INDEX
    Explanations

    details related to scientific measurements and atmospheric conditions

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and measurements related to environmental factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertising
    -0.98
    Kid
    -0.85
    killers
    -0.80
    selling
    -0.79
    Fighting
    -0.78
     hurting
    -0.77
    deal
    -0.77
    doing
    -0.76
     perks
    -0.76
     Whoever
    -0.75
    POSITIVE LOGITS
     âμ
    1.25
     equilibrium
    1.22
     epoch
    1.15
     sampled
    1.15
     spectral
    1.13
     observations
    1.13
     amplitude
    1.12
     isot
    1.12
     simulations
    1.11
     gradient
    1.10
    Activations Density 0.706%

    No Known Activations