INDEX

Explanations

instances of the word "appear."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

swt

-0.73

робнее

-0.69

 requestCode

-0.69

("/{

-0.68

言うと

-0.68

RuleContext

-0.66

λευτα

-0.64

PathVariable

-0.63

ymce

-0.62

 numele

-0.62

POSITIVE LOGITS

 appear

3.02

 appears

2.80

 Appear

2.72

 appeared

2.70

 Appears

2.57

 appearing

2.56

appears

2.49

appear

2.47

 APPE

2.32

Appear

2.31

Activations Density 0.066%

instances of the word "appear."

No Comments

No Known Activations