© 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. 14599
    Prev
    Next
    INDEX
    Explanations

    aggressive or intense actions or expressions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to extreme or intense states of being

    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
    ection
    -0.67
    perture
    -0.67
    Synopsis
    -0.66
     Flavoring
    -0.65
     Eg
    -0.64
    Translation
    -0.63
    catentry
    -0.62
    Introduced
    -0.62
     Fram
    -0.61
    ashington
    -0.58
    POSITIVE LOGITS
    Ô
    0.92
     unnoticed
    0.83
    ardless
    0.74
    ither
    0.73
    onz
    0.69
    eper
    0.69
    ternally
    0.69
     undet
    0.69
    ĸļ
    0.66
     lengths
    0.66
    Activations Density 0.196%

    No Known Activations