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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 8855
    Prev
    Next
    INDEX
    Explanations

    patterns of sentences or phrases ending in "to a [quality] extent"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" followed by related nouns or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    evidence
    -0.78
     indications
    -0.73
    packages
    -0.69
    /-
    -0.69
     indicators
    -0.67
    adin
    -0.63
     Eyes
    -0.62
     instructions
    -0.61
    tery
    -0.61
     alerts
    -0.60
    POSITIVE LOGITS
    venge
    1.38
    rouse
    1.21
     maximum
    0.82
     whopping
    0.81
     manageable
    0.80
     plethora
    0.80
     few
    0.78
     lesser
    0.77
     halt
    0.77
     couple
    0.77
    Activations Density 0.095%

    No Known Activations