INDEX

Explanations

negative contractions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

脚注の使い方

-0.89

AndEndTag

-0.67

 AssemblyCulture

-0.64

setViewportView

-0.63

styleType

-0.62

NewUrlParser

-0.58

errHandler

-0.58

Autoritní

-0.57

 démocr

-0.56

 avoient

-0.56

POSITIVE LOGITS

“

0.65

tag

0.63

“

0.61

 tags

0.59

tag

0.59

0.56

 source

0.55

Tag

0.55

tagged

0.55

thinking

0.55

Activations Density 0.041%

negative contractions

No Comments

No Known Activations