© 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. 3-RES-JB
    11. 12577
    Prev
    Next
    INDEX
    Explanations

    terms related to intense or extreme experiences

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives and adverbs that convey intense or unusual qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REL
    -0.77
    ramid
    -0.77
    hirt
    -0.74
    annis
    -0.74
    avez
    -0.70
    ploma
    -0.70
    owler
    -0.62
    antics
    -0.62
    adr
    -0.62
    hog
    -0.62
    POSITIVE LOGITS
    ly
    2.26
    LY
    1.38
    lys
    1.14
    fully
    1.09
    edly
    1.06
    liness
    1.05
    ously
    1.04
    ELY
    1.04
    ity
    1.02
    leys
    0.96
    Activations Density 0.055%

    No Known Activations