© 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. 10-RES-JB
    11. 2926
    Prev
    Next
    INDEX
    Explanations

    words related to physical sensation or feeling, especially those related to negative emotions

    oai_token-act-pair · gpt-3.5-turbo

    variants of the word "gnostic," referencing Gnostic beliefs or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ferry
    -0.74
     CONTIN
    -0.71
    staking
    -0.70
    âĹ¼
    -0.69
     lobe
    -0.64
     Gamble
    -0.62
    ëĭ
    -0.60
     tune
    -0.59
     spirited
    -0.58
     NB
    -0.58
    POSITIVE LOGITS
    ostic
    1.45
    osis
    1.35
    ome
    1.31
    ostics
    1.23
    omes
    1.22
    omic
    1.13
    omon
    1.13
    asher
    1.05
    arl
    1.02
    olls
    1.01
    Activations Density 0.041%

    No Known Activations