INDEX

Explanations

phrases related to communication or interaction

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

fromnode

-0.66

abestanden

-0.63

 lunghi

-0.63

 particuliers

-0.63

 florales

-0.62

 uovo

-0.61

 sedia

-0.60

 mécanique

-0.58

Packard

-0.57

 AppBundle

-0.56

POSITIVE LOGITS

 interviewed

0.77

 interloc

0.74

 conversation

0.73

Interview

0.73

 interview

0.73

 Gespräche

0.73

 Gespräch

0.72

 interviewing

0.71

 interrog

0.71

 Interview

0.70

Activations Density 0.145%

phrases related to communication or interaction

No Comments

No Known Activations