© 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. 2-RES-JB
    11. 17554
    Prev
    Next
    INDEX
    Explanations

    words related to the process of "ting", such as "maltting" or "netting"

    oai_token-act-pair · gpt-3.5-turbo

    words relating to the act of "ting" or activities associated with producing or engaging in a tingling sensation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.72
     cannabin
    -0.69
     reviewing
    -0.66
    vernment
    -0.66
    ici
    -0.64
     paramed
    -0.63
    £ı
    -0.63
    STD
    -0.63
    CRIP
    -0.61
    CONCLUS
    -0.61
    POSITIVE LOGITS
    ting
    1.46
    ted
    1.10
    ton
    1.09
    staking
    1.00
    mouth
    0.98
    ters
    0.90
    tering
    0.89
    pent
    0.89
    nel
    0.88
    ter
    0.87
    Activations Density 0.015%

    No Known Activations