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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18221
    Prev
    Next
    INDEX
    Explanations

    phrases related to power dynamics and influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate pressure and significant signals or messages

    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
    cknow
    -0.75
     aloud
    -0.64
    vich
    -0.62
     owning
    -0.61
    Ħ¢
    -0.60
     outnumbered
    -0.60
    abis
    -0.59
     wisely
    -0.58
     supplemented
    -0.57
     submitting
    -0.56
    POSITIVE LOGITS
     morale
    0.81
     havoc
    0.79
     surprises
    0.75
     nerve
    0.74
     impression
    0.73
     impetus
    0.72
     headaches
    0.69
     logistical
    0.69
     credibility
    0.68
    impact
    0.68
    Activations Density 0.468%

    No Known Activations