© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22649
    Prev
    Next
    INDEX
    Explanations

    explicit lists mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "list of."

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

    No Comments

    Negative Logits
    entimes
    -0.61
    cape
    -0.61
    imet
    -0.60
     whisper
    -0.59
     Mehran
    -0.59
    iva
    -0.59
     realise
    -0.59
     breeze
    -0.58
     ende
    -0.58
     estimate
    -0.58
    POSITIVE LOGITS
     sorts
    1.00
     entries
    0.77
    ãĥ¼ãĥ³
    0.77
    çĦ
    0.68
    Topics
    0.67
    edes
    0.65
     Excellence
    0.65
     highlights
    0.63
     accomplishments
    0.62
     HERO
    0.61
    Activations Density 0.097%

    No Known Activations