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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12051
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Kolpak" followed by a specific numerical value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kol" and its variations in different contexts

    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
    natureconservancy
    -1.01
    س
    -0.88
    ãĥ´ãĤ¡
    -0.83
    ا
    -0.82
    ÙĬ
    -0.81
    ãĥķ
    -0.80
    ÙĦ
    -0.79
    ع
    -0.79
    Interstitial
    -0.78
    Ø
    -0.77
    POSITIVE LOGITS
    oscope
    1.04
    edi
    0.77
    osc
    0.75
    oi
    0.72
     Kol
    0.71
    forward
    0.71
    osen
    0.70
    obl
    0.70
    ebin
    0.70
     Wick
    0.69
    Activations Density 0.027%

    No Known Activations