© 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. 2-RES-JB
    11. 13946
    Prev
    Next
    INDEX
    Explanations

    Proper nouns, especially names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities with the suffix 'ger'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     affirmative
    -0.70
    staking
    -0.63
    efeated
    -0.63
     Historic
    -0.62
     textual
    -0.61
     "{
    -0.59
    ccording
    -0.59
    endant
    -0.59
     excluding
    -0.58
     divided
    -0.58
    POSITIVE LOGITS
    ger
    1.08
    GER
    0.95
    gers
    0.94
    rors
    0.88
    rier
    0.86
    wolves
    0.81
    affe
    0.78
    fest
    0.77
    rants
    0.77
    adish
    0.77
    Activations Density 0.009%

    No Known Activations