INDEX

Explanations

terms related to extreme conditions or states

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

انجليز

-0.81

IsContent

-0.76

__()

-0.72

Sal

-0.69

tvguidetime

-0.69

Mosa

-0.67

 فريبيس

-0.66

ings

-0.66

وامل

-0.66

 segni

-0.65

POSITIVE LOGITS

 Xtreme

1.25

 Extreme

1.13

Extreme

1.01

 extrema

0.97

 extre

0.97

 extrême

0.96

 ekst

0.96

 extreme

0.94

treme

0.92

 Extre

0.87

Activations Density 0.094%

terms related to extreme conditions or states

No Comments

No Known Activations