INDEX

Explanations

mentions related to food and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

İstinadlar

-0.68

دانشنامهٔ

-0.66

 ujednoznacz

-0.61

XmlAccessorType

-0.61

 uParam

-0.59

__*/

-0.58

setopt

-0.57

retty

-0.55

CascadeType

-0.55

appoint

-0.55

POSITIVE LOGITS

 consumption

1.33

 consuming

1.30

 consume

1.28

 consumed

1.13

consumption

1.10

 eating

1.09

 Consumption

1.07

 CONSUM

1.04

eat

1.03

Consumption

1.01

Activations Density 0.218%

mentions related to food and dining experiences

No Comments

No Known Activations