© 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. 8-RES-JB
    11. 7750
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-improvement and development

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to self-improvement and enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Straw
    -0.80
    cia
    -0.73
    wave
    -0.67
    itto
    -0.66
    mad
    -0.66
    NetMessage
    -0.66
    usha
    -0.65
    ãĥĪ
    -0.65
    runners
    -0.65
    ansas
    -0.64
    POSITIVE LOGITS
     efficiency
    0.96
     productivity
    0.91
     responsiveness
    0.87
     acquainted
    0.83
     materially
    0.83
    ments
    0.81
    iating
    0.81
     relations
    0.81
     markedly
    0.80
     outcomes
    0.80
    Activations Density 0.058%

    No Known Activations