INDEX

Explanations

phrases indicating personal feelings and emotional expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

SBATCH

-0.88

########.

-0.88



-0.86

 ddelweddau

-0.84

 Мексичка

-0.82

帖最后由

-0.81

ThroughAttribute

-0.80

 Heeren

-0.80

IVEREF

-0.78

 Cæsar

-0.77

POSITIVE LOGITS

0.58

Band

0.46

дачи

0.44

erol

0.44

woh

0.43

Fa

0.42

 مل

0.42

ves

0.42

neos

0.41

om

0.41

Activations Density 0.081%

phrases indicating personal feelings and emotional expressions

No Comments

No Known Activations