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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18171
    Prev
    Next
    INDEX
    Explanations

    the word "from" with various suffixes or prefixes attached to it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "rom" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rapids
    -0.66
     reminders
    -0.66
    Notes
    -0.65
    Ĵ
    -0.64
     Citation
    -0.63
    Tags
    -0.63
     Jackets
    -0.63
     Staples
    -0.63
     Padres
    -0.62
     haste
    -0.62
    POSITIVE LOGITS
    antic
    1.28
    astery
    1.18
    agnetic
    1.11
    ancers
    1.08
    ecast
    1.08
    antically
    1.04
    rom
    1.00
    emo
    0.98
    antics
    0.96
    orph
    0.95
    Activations Density 0.007%

    No Known Activations