© 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. 18344
    Prev
    Next
    INDEX
    Explanations

    words related to raising one's voice or shouting in a loud manner

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "yelling at" in various contexts

    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
    glass
    -0.75
    Cert
    -0.74
    BuyableInstoreAndOnline
    -0.73
    CLASS
    -0.71
    per
    -0.70
    cert
    -0.69
    Lens
    -0.69
    phone
    -0.69
    hops
    -0.68
    mingham
    -0.67
    POSITIVE LOGITS
     least
    1.13
     halftime
    0.89
     dusk
    0.88
     nighttime
    0.80
     midnight
    0.80
    rial
    0.80
    ĸļ
    0.79
     midday
    0.76
     sunset
    0.75
     whim
    0.74
    Activations Density 0.205%

    No Known Activations