INDEX

Explanations

terms related to hovering or overlapping actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

//

-0.77

BeginContext

-0.73

надца

-0.73

 handleMessage

-0.67

-0.66

 OMITBAD

-0.65

othea

-0.64

 Rudi

-0.63

oplayer

-0.62

alace

-0.61

POSITIVE LOGITS

hover

2.27

 hover

2.06

Hover

1.89

 Hover

1.78

 hovered

1.59

 hovering

1.57

 lingered

0.83

 éter

0.76

drift

0.75

 Drift

0.75

Activations Density 0.036%

terms related to hovering or overlapping actions

No Comments

No Known Activations