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. 4-RES-JB
    6. 3922
    Prev
    Next
    INDEX
    Explanations

    biographical information about notable figures in various fields

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures or events

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

    No Comments

    Negative Logits
     tremend
    -0.71
    ccording
    -0.68
     apologies
    -0.66
     corrid
    -0.63
     polarized
    -0.63
     resil
    -0.61
     resolutions
    -0.59
     demographics
    -0.58
     polarization
    -0.57
     unnecess
    -0.57
    POSITIVE LOGITS
    ova
    0.87
    iev
    0.85
     âĵĺ
    0.82
    ensis
    0.78
    oglu
    0.76
    ichi
    0.76
     III
    0.75
    eker
    0.75
    agh
    0.74
    enko
    0.74
    Activations Density 0.623%

    No Known Activations