INDEX

Explanations

references to food items and culinary experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

AddTagHelper

-0.66

IonicModule

-0.60

NewUrlParser

-0.59

ControllerAdvice

-0.55

principalColumn

-0.54

 Frick

-0.51

ctical

-0.50

cerely

-0.48

 Italijani

-0.48

ValueMap

-0.47

POSITIVE LOGITS

 served

1.12

 topped

0.91

 Served

0.90

served

0.83

 garn

0.82

 smothered

0.79

dri

0.77

 prepared

0.75

 servido

0.74

 flamb

0.71

Activations Density 0.199%

references to food items and culinary experiences

No Comments

No Known Activations