INDEX

Explanations

references to text and text-related concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-1.18

 تضيفلها

-1.11

 combineReducers

-1.03

SBATCH

-1.03

клопе

-1.01

ConstraintMaker

-0.99

 ostavi

-0.98

expandindo

-0.98

 ligiloj

-0.98

 يتيمه

-0.95

POSITIVE LOGITS

 text

2.61

 Text

2.37

 TEXT

2.18

 texts

2.15

text

2.13

Text

2.12

TEXT

2.03

 Texts

1.75

 texte

1.74

 texto

1.63

Activations Density 0.074%

references to text and text-related concepts

No Comments

No Known Activations