© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19785
    Prev
    Next
    INDEX
    Explanations

    sentences expressing strong emotions or concerns about different situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express strong emotional responses

    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
     Millennium
    -0.75
    amins
    -0.74
    ordan
    -0.72
     Guys
    -0.70
    rules
    -0.70
    arters
    -0.69
    othy
    -0.69
    ulia
    -0.67
    iful
    -0.66
     Citation
    -0.65
    POSITIVE LOGITS
     ingrained
    0.98
     rooted
    0.90
     immersed
    0.86
     embedded
    0.85
     engaged
    0.84
     enough
    0.82
     connected
    0.82
     entrenched
    0.81
     seated
    0.79
    ened
    0.78
    Activations Density 0.009%

    No Known Activations