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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 23620
    Prev
    Next
    INDEX
    Explanations

    terms related to adjustments or balance in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    attributes related to adjustments, balance, and emotional states

    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
     signature
    -0.82
     wire
    -0.77
     countdown
    -0.75
     mushrooms
    -0.73
     chant
    -0.71
     nap
    -0.71
     grav
    -0.71
     lav
    -0.70
    eters
    -0.69
     reign
    -0.68
    POSITIVE LOGITS
    adjusted
    2.86
    rounded
    2.46
    balanced
    2.09
    broken
    2.04
    meaning
    1.66
    average
    1.29
    intention
    1.26
    edited
    1.26
    biased
    1.22
    balance
    1.20
    Activations Density 0.039%

    No Known Activations