© 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. 6-RES-JB
    11. 2867
    Prev
    Next
    INDEX
    Explanations

    words related to the prefix "rom", which can imply a sense of romanticism or technology

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "rom" in text

    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
     Rapids
    -0.73
     Pacers
    -0.64
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.64
     haste
    -0.64
     Jackets
    -0.64
    gerald
    -0.62
     Reserve
    -0.62
     reminders
    -0.61
     Venezuela
    -0.61
    Notes
    -0.61
    POSITIVE LOGITS
    ecast
    1.22
    antic
    1.15
    ancers
    1.14
    astery
    1.10
    agnetic
    1.05
    antically
    1.02
    otive
    0.98
    orph
    0.98
    antics
    0.95
    edia
    0.95
    Activations Density 0.013%

    No Known Activations