INDEX

Explanations

comparative phrases indicating differences between groups or variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

égard

-0.45

 actualidad

-0.45

tri

-0.43

为了

-0.43

cam

-0.42

 égard

-0.42

hecho

-0.40

LEX

-0.40

為了

-0.39

parin

-0.39

POSITIVE LOGITS

RTLD

0.77

EndContext

0.76

 wireType

0.75

tanleria

0.75

])));

0.74

Hentet

0.72

sizeCache

0.72

saraba

0.72

resizingMask

0.71

 propOrder

0.70

Activations Density 0.267%

comparative phrases indicating differences between groups or variables

No Comments

No Known Activations