© 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. 11-RES-JB
    11. 9938
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "So"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "So" in various contexts, indicating a transition or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "},"
    -0.68
    /
    -0.63
     ])
    -0.56
    unc
    -0.56
    icipated
    -0.55
    uc
    -0.55
    taboola
    -0.55
    ĸļ
    -0.54
    ICT
    -0.54
    ãĥį
    -0.54
    POSITIVE LOGITS
    oner
    1.34
     yeah
    1.15
     far
    1.11
    fter
    0.98
     why
    0.96
     basically
    0.91
    adays
    0.90
     yea
    0.89
     yes
    0.89
    FTWARE
    0.89
    Activations Density 0.056%

    No Known Activations