© 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. 2-RES-JB
    11. 17668
    Prev
    Next
    INDEX
    Explanations

    terms related to variability or change

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "variation" and related forms

    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
    ×Ļ
    -0.78
    ת
    -0.76
    stra
    -0.76
    ãĥİ
    -0.76
    Ķ
    -0.70
     Arrows
    -0.69
    ×Ķ
    -0.68
    ×Ļ×
    -0.68
    JECT
    -0.66
    ×IJ
    -0.65
    POSITIVE LOGITS
    arily
    1.14
    yip
    1.02
     variations
    0.96
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.95
     variation
    0.94
     Vari
    0.94
    aution
    0.92
    dayName
    0.85
    ĸļ
    0.84
    soType
    0.83
    Activations Density 0.010%

    No Known Activations