© 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. 0-RES-JB
    11. 2438
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly ones related to politics, organizations, or individuals

    oai_token-act-pair · gpt-3.5-turbo

    the word "bas" and its variations or related derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curfew
    -0.84
     Vaughan
    -0.76
     enforced
    -0.65
     Migration
    -0.64
     Personality
    -0.62
     Enterprise
    -0.60
     feminism
    -0.60
     homosexuality
    -0.59
     disability
    -0.59
     eviction
    -0.59
    POSITIVE LOGITS
    bas
    4.16
    Bas
    1.95
     Bas
    1.55
    bass
    1.36
    vas
    1.30
     bas
    1.28
    lins
    1.24
    bi
    1.10
     BAS
    1.08
    thus
    1.07
    Activations Density 0.020%

    No Known Activations