© 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. 10-RES-JB
    11. 10619
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizing and arranging things

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" along with phrases emphasizing organization or being in a favorable situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gling
    -0.73
    ¿½
    -0.73
    ague
    -0.72
    Missing
    -0.69
    hai
    -0.65
    Invalid
    -0.63
    opus
    -0.62
    mere
    -0.61
    bara
    -0.60
    ¶ħ
    -0.60
    POSITIVE LOGITS
     sync
    1.05
     tune
    1.01
     harmony
    0.98
     shape
    0.96
     compliance
    0.95
     accordance
    0.92
    offensive
    0.91
     line
    0.87
     touch
    0.87
     conformity
    0.85
    Activations Density 0.138%

    No Known Activations