INDEX

Explanations

phrases emphasizing the importance or significance of a concept, fact, or idea

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

 judicia

-0.70

 AppColors

-0.66

 pleaſure

-0.66

 houſe

-0.65

 Chriftian

-0.65

 judiciaire

-0.64

 ſche

-0.62

 Jefus

-0.62

 iconFacebook

-0.61

 ſch

-0.61

POSITIVE LOGITS

 same

0.88

 very

0.82

same

0.79

very

0.76

rungsseite

0.73

 stesso

0.72

Very

0.72

 Very

0.71

VERY

0.69

 VERY

0.69

Activations Density 0.060%

phrases emphasizing the importance or significance of a concept, fact, or idea

No Comments

No Known Activations