INDEX

Explanations

references to different forms of the word "Bay."

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

IndentedString

-0.91

 Anſ

-0.77

 Theſe

-0.72

adaptiveStyles

-0.72

Efq

-0.70

 OFDb

-0.69

 bezeichneter

-0.69

 Jefus

-0.67

rungsseite

-0.66

 againſt

-0.66

POSITIVE LOGITS

 area

0.65

bay

0.59

onets

0.58

Bay

0.57

view

0.56

rakt

0.55

 getView

0.55

 Area

0.54

Bay

0.54

area

0.53

Activations Density 0.104%

references to different forms of the word "Bay."

No Comments

No Known Activations