INDEX

Explanations

phrases related to criticism and statements about individuals or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 protoimpl

-0.63

 faveur

-0.62

 pernas

-0.56

KommentareTeilen

-0.55

racite

-0.55

DockStyle

-0.54

hourly

-0.53

charpe

-0.53

 mattino

-0.53

reshold

-0.52

POSITIVE LOGITS

 talking

0.65

発言

0.60

 speaking

0.58

Speaking

0.57

 declaraciones

0.56

 заяви

0.55

 talk

0.55

 δή

0.54

 Dijo

0.54

 confessed

0.54

Activations Density 0.308%

phrases related to criticism and statements about individuals or events

No Comments

No Known Activations