© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22147
    Prev
    Next
    INDEX
    Explanations

    GitHub URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs and links to online resources, particularly from GitHub and Twitter

    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
    ĪĴ
    -0.80
    ulhu
    -0.73
    ornia
    -0.73
    onics
    -0.66
    ERO
    -0.64
    Medic
    -0.63
     Reincarn
    -0.62
     proportions
    -0.62
     mug
    -0.62
     Siren
    -0.62
    POSITIVE LOGITS
    groups
    0.79
    pages
    0.71
     buttons
    0.70
    },"
    0.69
    username
    0.68
    theless
    0.68
    foo
    0.66
    /
    0.66
    ":["
    0.65
     Michaels
    0.65
    Activations Density 0.052%

    No Known Activations