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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23317
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching or sifting through information

    oai_token-act-pair · gpt-3.5-turbo

    instances of navigating or filtering through information and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eli
    -0.78
    hel
    -0.77
    KO
    -0.73
    interstitial
    -0.72
    VO
    -0.71
    erto
    -0.71
    kas
    -0.70
    voice
    -0.67
    kiss
    -0.67
    Brand
    -0.66
    POSITIVE LOGITS
     archives
    0.84
     logs
    0.83
     scrolls
    0.77
     menus
    0.75
     browsing
    0.73
     databases
    0.71
     recess
    0.71
     scriptures
    0.68
     bins
    0.68
     histories
    0.67
    Activations Density 0.113%

    No Known Activations