INDEX

Explanations

the beginning of different sections or concepts in documents

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 redenen

-0.95

 mijne

-0.90

 belangrij

-0.89

 moeite

-0.88

 gebou

-0.84

 persoons

-0.81

kjø

-0.79

UVWXYZ

-0.76

 Wikiseite

-0.73

 wikipagina

-0.73

POSITIVE LOGITS

het

0.91

een

0.83

van

0.82

Het

0.81

IsContent

0.81

HasIndex

0.80

Het

0.80

Een

0.76

 ThemeData

0.74

 uska

0.74

Activations Density 0.002%

the beginning of different sections or concepts in documents

No Comments

No Known Activations