© 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. 13420
    Prev
    Next
    INDEX
    Explanations

    positive and enthusiastic words

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement or enthusiasm

    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
    ©¶æ
    -0.99
    nery
    -0.84
    avis
    -0.80
    bey
    -0.72
    arer
    -0.68
    ada
    -0.67
    ele
    -0.66
    xia
    -0.66
    avia
    -0.66
    pel
    -0.66
    POSITIVE LOGITS
    ly
    0.85
     exciting
    0.80
    rament
    0.76
    GGGGGGGG
    0.76
     new
    0.73
     opportunities
    0.73
     developments
    0.72
     entreprene
    0.71
     tid
    0.70
     prospects
    0.69
    Activations Density 0.010%

    No Known Activations