INDEX

Explanations

terms related to navigation elements in a user interface

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RectangleBorder

-0.62

parsedMessage

-0.61

HtmlAttribute

-0.58

ThroughAttribute

-0.58

Tch

-0.58

}{*}{}

-0.56

niosek

-0.56

umenten

-0.56

timewa

-0.56

CompilerServices

-0.55

POSITIVE LOGITS

nav

0.94

Nav

0.87

Nav

0.82

NAV

0.74

 navigation

0.71

nav

0.69

 Navig

0.67

 navigational

0.65

NAV

0.64

 Navigation

0.63

Activations Density 0.046%

terms related to navigation elements in a user interface

No Comments

No Known Activations