© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20635
    Prev
    Next
    INDEX
    Explanations

    words related to various forms of actions ending in 'ting', including different tenses and types of actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or processes that involve physical interaction or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anmar
    -0.74
    £ı
    -0.74
    åħī
    -0.71
     cannabin
    -0.67
    vernment
    -0.65
    åij
    -0.64
     subdu
    -0.62
    éĹĺ
    -0.62
     JPM
    -0.60
    actionDate
    -0.60
    POSITIVE LOGITS
    ting
    1.17
    mouth
    1.08
    ted
    0.97
    nel
    0.96
    ty
    0.94
    ton
    0.91
    ter
    0.89
    ters
    0.89
    lon
    0.87
    ius
    0.85
    Activations Density 0.056%

    No Known Activations