© 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. 22276
    Prev
    Next
    INDEX
    Explanations

    phrases related to letting go or release

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "let go."

    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
    orno
    -0.72
    ablo
    -0.63
     Watkins
    -0.60
    creen
    -0.59
     Mub
    -0.59
    itionally
    -0.57
    orney
    -0.57
    itu
    -0.56
    icion
    -0.56
    ________
    -0.54
    POSITIVE LOGITS
     overboard
    0.87
    vt
    0.86
    verning
    0.81
     limp
    0.81
    onies
    0.79
    lems
    0.79
    ogl
    0.70
     nuts
    0.70
     Away
    0.68
    aded
    0.68
    Activations Density 0.058%

    No Known Activations