© 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. 0-RES-JB
    11. 1489
    Prev
    Next
    INDEX
    Explanations

    numerical terms or technical references

    oai_token-act-pair · gpt-3.5-turbo

    specific sections or parts of documents, particularly those labeled as "PART" or related to structured content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estone
    -0.74
    ocr
    -0.73
    rim
    -0.72
    igree
    -0.72
    lam
    -0.71
     Glas
    -0.70
    brid
    -0.70
    ocratic
    -0.67
    oho
    -0.67
    asu
    -0.65
    POSITIVE LOGITS
    PART
    2.37
     guessing
    1.88
    NOTE
    1.41
     PART
    1.20
    azard
    1.10
     NOTE
    0.96
     checkout
    0.91
    Ware
    0.90
     TABLE
    0.86
    9999
    0.83
    Activations Density 0.054%

    No Known Activations