© 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. 9252
    Prev
    Next
    INDEX
    Explanations

    references to a specific organization or brand

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Marvel Cinematic Universe (MCU)

    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
     Gingrich
    -0.78
    ãĥ³ãĤ¸
    -0.77
    ãĤ¦ãĤ¹
    -0.74
     Meier
    -0.73
    ãĥ¼ãĥĨ
    -0.72
    ãĥł
    -0.72
    éĹĺ
    -0.70
    ãĥ¼ãĥ
    -0.70
    uyomi
    -0.69
    âķIJâķIJ
    -0.68
    POSITIVE LOGITS
    MC
    1.26
    intosh
    0.96
    abre
    0.87
    SA
    0.87
    illion
    0.87
    GRE
    0.85
    SC
    0.82
     MC
    0.81
    SP
    0.80
    GUI
    0.79
    Activations Density 0.006%

    No Known Activations