© 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. 18170
    Prev
    Next
    INDEX
    Explanations

    phrases related to organization or management of tasks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in" indicating location or context

    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
    ¿½
    -0.75
     discrep
    -0.73
    Missing
    -0.71
    gling
    -0.67
    Invalid
    -0.67
    ague
    -0.66
    jit
    -0.65
     incomp
    -0.64
    FML
    -0.63
    icides
    -0.62
    POSITIVE LOGITS
     shape
    1.13
     sync
    1.00
    shape
    0.98
     touch
    0.94
     tune
    0.94
     harmony
    0.93
     line
    0.92
     compliance
    0.91
    offensive
    0.90
     place
    0.89
    Activations Density 0.123%

    No Known Activations