© 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. 10-RES-JB
    11. 10164
    Prev
    Next
    INDEX
    Explanations

    phrases related to impactful or significant contributions

    oai_token-act-pair · gpt-3.5-turbo

    key phrases related to important reports or findings

    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
    enery
    -0.81
    existent
    -0.81
     sucks
    -0.78
     hating
    -0.78
     pesky
    -0.67
    suff
    -0.66
     hates
    -0.65
    evil
    -0.64
     Evil
    -0.64
     scares
    -0.64
    POSITIVE LOGITS
     culmination
    1.30
     continuation
    1.05
     centerpiece
    1.04
     collaboration
    1.02
     cornerstone
    1.02
     testament
    0.99
     successor
    0.96
     precursor
    0.89
     collaborative
    0.88
     homage
    0.86
    Activations Density 0.267%

    No Known Activations