© 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. 724
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate examples or instances of something

    oai_token-act-pair · gpt-3.5-turbo

    the word "Such" used to introduce examples or statements

    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
    Ö¼
    -0.66
    uay
    -0.66
    kick
    -0.64
     Drum
    -0.64
    olate
    -0.64
    emies
    -0.63
    creen
    -0.63
    office
    -0.63
    ̶
    -0.62
    oil
    -0.61
    POSITIVE LOGITS
    ities
    0.78
     matters
    0.77
    ties
    0.73
     considerations
    0.66
     embodiments
    0.65
     factors
    0.65
    minded
    0.64
     cancell
    0.64
    fter
    0.63
     minded
    0.63
    Activations Density 0.029%

    No Known Activations