INDEX

Explanations

specific programming or technical terms within the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 raiſ

-0.74

+:+

-0.71

Portale

-0.70

/>\

-0.67

 uſed

-0.66

 TimeUnit

-0.66

NUMX

-0.66

MatInputModule

-0.66

Filmographie

-0.65

roux

-0.65

POSITIVE LOGITS

0.65

er

0.58

↵↵

0.56

mi

0.55

0.54

ut

0.53

ss

0.53

gu

0.53

ic

0.53

libft

0.53

Activations Density 0.180%

specific programming or technical terms within the text

No Comments

No Known Activations