INDEX

Explanations

terms related to the concept of "wrapping" or "enclosing."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 bezeichneter

-0.57

 FetchType

-0.54

 CURIAM

-0.51

 bordada

-0.50

 GenerationType

-0.49

 odkazy

-0.46

Література

-0.46

rungsseite

-0.46

 nocturno

-0.46

MigrationBuilder

-0.46

POSITIVE LOGITS

 wrapped

0.63

 wrapper

0.62

wrapper

0.60

 wrapping

0.60

 vision

0.59

 Wrapper

0.59

 wrap

0.58

vision

0.57

 Wrapping

0.55

wra

0.54

Activations Density 1.885%

terms related to the concept of "wrapping" or "enclosing."

No Comments

No Known Activations