INDEX

Explanations

emotional responses and critiques related to storytelling

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

annoyance or frustration

np_acts-logits-general · gemini-2.0-flash

annoying, infuriating, frustrating

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

esModule

-0.44

ština

-0.41

lamine

-0.41

paž

-0.41

ISTER

-0.40

Rec

-0.39

camin

-0.39

stande

-0.39

Vis

-0.39

Du

-0.39

POSITIVE LOGITS

 annoy

1.34

 infuriating

1.27

 annoying

1.25

 irritate

1.24

 frust

1.20

 irritating

1.19

 frustrating

1.18

frust

1.18

 annoys

1.17

 frustrate

1.14

Activations Density 0.286%

emotional responses and critiques related to storytelling

annoyance or frustration

annoying, infuriating, frustrating

No Comments

No Known Activations