INDEX

Explanations

terms related to wrapping

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 الرياضيه

-0.86

 <=",

-0.75

Билгалдахарш

-0.66

مصادر

-0.66

 Roskov

-0.64

GSP

-0.64

usehen

-0.64

 ComVisible

-0.64

 يتيمه

-0.62

DockStyle

-0.61

POSITIVE LOGITS

 Wrap

0.86

 wrap

0.84

 wrapped

0.77

wrap

0.73

 wrapping

0.72

wrapped

0.70

Wrap

0.67

 wraps

0.67

 Wrapping

0.66

__':

0.65

Activations Density 0.059%

terms related to wrapping

No Comments

No Known Activations