© 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. 10583
    Prev
    Next
    INDEX
    Explanations

    phrases related to feelings of safety, comfort, and discomfort

    oai_token-act-pair · gpt-3.5-turbo

    emotions related to safety and comfort

    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
     recovered
    -0.63
     Airl
    -0.63
    angler
    -0.62
    odder
    -0.62
     Appears
    -0.61
    adra
    -0.60
    nm
    -0.60
    }"
    -0.58
    ummer
    -0.58
    tein
    -0.58
    POSITIVE LOGITS
    ULAR
    0.78
    vier
    0.63
    ient
    0.62
    Discuss
    0.61
    tics
    0.61
    Tur
    0.60
    ety
    0.59
    Premium
    0.59
    âĿ
    0.57
    uku
    0.57
    Activations Density 0.091%

    No Known Activations