© 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. 11-RES-JB
    11. 18505
    Prev
    Next
    INDEX
    Explanations

    statistics and demographics related to various groups of people

    oai_token-act-pair · gpt-3.5-turbo

    demographic statistics related to marginalized communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¶
    -0.79
    æĦ
    -0.71
    ollah
    -0.70
    Especially
    -0.70
    dfx
    -0.69
    tnc
    -0.66
    ¬¼
    -0.65
     extraord
    -0.64
    inventoryQuantity
    -0.63
    padding
    -0.62
    POSITIVE LOGITS
     surveyed
    1.42
     polled
    1.30
     disapprove
    1.01
     identify
    1.00
     reside
    0.99
     approve
    0.98
     admit
    0.97
     participated
    0.96
     identifies
    0.94
     voted
    0.92
    Activations Density 0.163%

    No Known Activations