© 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. 7-RES-JB
    11. 1626
    Prev
    Next
    INDEX
    Explanations

    statements indicating support or backing from different sources

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating support or backing from various entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trap
    -0.86
    perfect
    -0.84
    orio
    -0.84
    hemer
    -0.83
    iated
    -0.82
    enth
    -0.82
    iae
    -0.81
    inis
    -0.81
    apes
    -0.80
    empl
    -0.80
    POSITIVE LOGITS
     allies
    0.81
     assurances
    0.80
     credible
    0.80
     supplying
    0.75
     grants
    0.75
     goodwill
    0.74
     promises
    0.73
     alliances
    0.73
     patronage
    0.71
     billions
    0.71
    Activations Density 0.109%

    No Known Activations