© 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. 1-RES-JB
    11. 18711
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration or partnership

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to collaboration and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uters
    -0.77
    uter
    -0.68
     Nar
    -0.65
    yre
    -0.64
     Rite
    -0.63
     Centauri
    -0.62
    vae
    -0.62
    emb
    -0.61
    ently
    -0.61
    ruption
    -0.61
    POSITIVE LOGITS
     teamed
    1.09
    ãĥĦ
    0.93
    ãĤ¤ãĥĪ
    0.84
    éĹĺ
    0.82
    romeda
    0.80
    æ©
    0.79
    ĸļ
    0.75
    ingen
    0.74
    pants
    0.72
    SourceFile
    0.71
    Activations Density 0.006%

    No Known Activations