Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6605
    Prev
    Next
    INDEX
    Explanations

    terms related to productivity and efficiency

    oai_token-act-pair · gpt-3.5-turbo

    terms related to productivity and accountability

    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
    •single token firings
    Individually fires on " wellness", " mindfulnes", " accountability", " wellbeing", " sustainability"

    No Comments

    Negative Logits
    rez
    -1.03
    entious
    -0.84
    ochet
    -0.80
    geries
    -0.77
    asel
    -0.75
    uga
    -0.75
    zynski
    -0.73
    enna
    -0.73
    gery
    -0.73
    inal
    -0.72
    POSITIVE LOGITS
     enh
    0.86
     assurance
    0.85
     quot
    0.83
     enhancement
    0.83
     Enh
    0.82
    ful
    0.81
     enhancing
    0.80
     advoc
    0.80
     Enhancement
    0.79
     initiatives
    0.77
    Activations Density 0.235%

    No Known Activations