© 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. 18451
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions or impactful events

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to strong emotions and significant impacts

    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
    nder
    -0.62
     Aly
    -0.59
     nearest
    -0.58
    most
    -0.56
    equ
    -0.55
     Rover
    -0.54
    adobe
    -0.53
     flick
    -0.53
    aleb
    -0.52
    uly
    -0.52
    POSITIVE LOGITS
     (>
    0.86
    PsyNetMessage
    0.64
    Marginal
    0.61
    minist
    0.61
    FactoryReloaded
    0.61
     warr
    0.60
    Initialized
    0.60
    00007
    0.59
    Ùĩ
    0.59
    ront
    0.58
    Activations Density 0.783%

    No Known Activations