© 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. 10-RES-JB
    11. 23521
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing support or care

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to healthcare, support, and social equality

    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
    ongo
    -0.65
    Interstitial
    -0.64
    onday
    -0.62
    bda
    -0.62
    igh
    -0.60
    arat
    -0.60
    nce
    -0.59
    isible
    -0.59
    ãĥ´
    -0.58
    ouple
    -0.57
    POSITIVE LOGITS
     necessary
    1.29
     needed
    1.26
     desired
    1.24
     required
    1.19
     requisite
    1.08
     they
    1.06
    needed
    1.05
    necessary
    1.02
     envisioned
    0.94
     we
    0.92
    Activations Density 0.362%

    No Known Activations