INDEX

Explanations

mentions of the term "ES" and related variations, indicating a focus on European languages or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

PerformLayout

-0.96

 Wallflower

-0.90

mingbird

-0.86

djangoproject

-0.83

MethodManager

-0.81

featureID

-0.81

fillType

-0.80

toJSONString

-0.79

ThroughAttribute

-0.78

POSITIVE LOGITS

ES

1.18

ES

1.13

es

1.01

Es

0.94

IES

0.93

VES

0.92

Es

0.91

 Beres

0.91

es

0.90

PES

0.89

Activations Density 0.202%

mentions of the term "ES" and related variations, indicating a focus on European languages or contexts

No Comments

No Known Activations