© 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. 7330
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "contents" within a text

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "contents."

    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
    roads
    -0.73
    ansson
    -0.71
    Äĩ
    -0.70
    ARP
    -0.64
     Rapp
    -0.62
    ño
    -0.61
    verbs
    -0.61
    arms
    -0.61
     Architects
    -0.60
    Vill
    -0.60
    POSITIVE LOGITS
     contents
    1.02
    ĸļ
    0.88
    afety
    0.86
    ascript
    0.86
    matter
    0.85
    ecause
    0.84
     Contents
    0.84
    ious
    0.83
    uggest
    0.77
    ions
    0.76
    Activations Density 0.013%

    No Known Activations