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. 8-RES-JB
    6. 19715
    Prev
    Next
    INDEX
    Explanations

    conjunctions connecting words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "and."

    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
    vec
    -0.76
    rued
    -0.72
    unes
    -0.71
    kamp
    -0.69
    baum
    -0.69
    ump
    -0.63
    dayName
    -0.63
    imum
    -0.62
    crop
    -0.60
    ]."
    -0.60
    POSITIVE LOGITS
     unable
    0.95
     preferably
    0.90
     hindsight
    0.89
     unheard
    0.84
     surrounded
    0.84
     possessing
    0.82
     lacking
    0.81
     needing
    0.81
     expecting
    0.80
     devoid
    0.80
    Activations Density 0.322%

    No Known Activations