© 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 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. 10-RES-JB
    11. 3409
    Prev
    Next
    INDEX
    Explanations

    phrases related to the release or availability of products and services

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a product's availability or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uca
    -0.75
    romy
    -0.74
    aghan
    -0.74
    ivas
    -0.74
    terness
    -0.69
    SOURCE
    -0.68
    ersen
    -0.68
    iger
    -0.68
    itiveness
    -0.68
    ashtra
    -0.67
    POSITIVE LOGITS
    ynchron
    1.15
     part
    1.09
     standalone
    0.99
     follows
    0.94
    pires
    0.94
    part
    0.91
    pired
    0.91
     soon
    0.85
    semb
    0.81
    ynchronous
    0.77
    Activations Density 0.112%

    No Known Activations