INDEX

Explanations

references to images

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 antar

-0.75

Revel

-0.74

RTEE

-0.73

 Becher

-0.72

findpost

-0.72

 Kall

-0.69

AutoScaleMode

-0.69

 AssemblyCulture

-0.68

 EconPapers

-0.68

 "$@"

-0.67

POSITIVE LOGITS

img

2.57

img

2.21

Img

1.53

IMG

1.40

Img

1.37

IMG

1.18

imgs

1.16

Imgs

1.15

 imgs

1.02

imgUrl

1.00

Activations Density 0.103%

references to images

No Comments

No Known Activations