© 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. 4-RES-JB
    11. 6852
    Prev
    Next
    INDEX
    Explanations

    phrases related to opening up emotionally or physically

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "open up"

    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
    mong
    -0.61
    _.
    -0.60
     num
    -0.59
     Kahn
    -0.59
    ]"
    -0.59
     disabling
    -0.58
    arily
    -0.57
    rouse
    -0.55
    >"
    -0.54
     Manson
    -0.54
    POSITIVE LOGITS
    riott
    0.84
    ended
    0.79
    olicy
    0.79
    adesh
    0.75
    stairs
    0.72
    izons
    0.72
    ris
    0.72
    river
    0.71
    Redd
    0.71
    skirts
    0.70
    Activations Density 0.032%

    No Known Activations