INDEX

Explanations

prepositions and connecting words that establish relationships between ideas

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

:+:

-1.02

 gawas

-0.96

✭✭

-0.90

^(@)

-0.89

+#+#

-0.87

لينكات

-0.87

หวัด

-0.86

numerusform

-0.85

ViewFeatures

-0.83

PhysRevD

-0.82

POSITIVE LOGITS

0.72

↵

0.63

↵↵

0.60

".

0.60

0.59

..."

0.54

The

0.53

0.52

Activations Density 0.713%

prepositions and connecting words that establish relationships between ideas

No Comments

No Known Activations