© 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. 17144
    Prev
    Next
    INDEX
    Explanations

    phrases related to stress relief techniques

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or sentence endings

    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
     scrap
    -0.93
    xual
    -0.75
     grap
    -0.67
     directly
    -0.67
     hashing
    -0.67
     bragging
    -0.67
    isans
    -0.67
     oval
    -0.64
    emis
    -0.64
     '.
    -0.64
    POSITIVE LOGITS
    Section
    1.01
    ?????-?????-
    0.90
    Cooldown
    0.90
    Newsletter
    0.87
    Write
    0.84
    ³³³³
    0.84
    Writing
    0.82
     Âł Âł Âł Âł
    0.81
    _(
    0.79
    ³³³³³³³³
    0.79
    Activations Density 0.368%

    No Known Activations