© 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. 3002
    Prev
    Next
    INDEX
    Explanations

    proper nouns such as places and names involved in incidents or crimes

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and verbs related to a specific individual in a narrative context

    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
     Watching
    -0.80
     disadvant
    -0.68
     Dominion
    -0.62
    Higher
    -0.59
     Gors
    -0.59
     Definitions
    -0.59
     Millenn
    -0.58
     Cities
    -0.57
     SEO
    -0.57
    Insert
    -0.57
    POSITIVE LOGITS
     underwent
    1.38
     remained
    1.15
     fled
    1.14
     was
    1.13
     surrendered
    1.10
     reportedly
    1.09
    'd
    1.08
     escaped
    1.07
     pleaded
    1.07
     suffered
    1.06
    Activations Density 0.256%

    No Known Activations