© 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. 1-RES-JB
    11. 20283
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Behrendt" and variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Beh and related behavioral terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ismo
    -0.77
    gling
    -0.72
    èª
    -0.69
     wheelchair
    -0.68
    intendent
    -0.67
    kefeller
    -0.67
    ç¥ŀ
    -0.66
    eous
    -0.66
    enthal
    -0.66
     Kaepernick
    -0.66
    POSITIVE LOGITS
     Beh
    1.27
    aviour
    1.25
    Beh
    0.93
    itters
    0.89
    avior
    0.83
    uate
    0.81
    abus
    0.80
    Ħ¢
    0.79
    beh
    0.79
    rou
    0.76
    Activations Density 0.012%

    No Known Activations