© 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. 17211
    Prev
    Next
    INDEX
    Explanations

    references to specific regions or products, particularly related to environmental or financial topics

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "ient" in words related to various subjects

    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
    mbuds
    -1.08
    AMS
    -0.79
    udeb
    -0.74
    MAR
    -0.73
    oldown
    -0.71
    wordpress
    -0.71
    ultz
    -0.71
    OWS
    -0.70
    UNCH
    -0.69
    shr
    -0.69
    POSITIVE LOGITS
    ial
    1.11
    ient
    1.10
    ially
    1.05
    ele
    0.83
    eers
    0.83
    eering
    0.80
    iency
    0.79
    aily
    0.78
    eer
    0.77
    ious
    0.73
    Activations Density 0.018%

    No Known Activations