INDEX

Explanations

notations or references that signify important information or observations

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

jooq

-0.61

 وسلم

-0.55

 nadzieję

-0.53

 czyn

-0.52

esterno

-0.51

ętr

-0.51

huit

-0.50

chapper

-0.49

gdx

-0.48

).__

-0.48

POSITIVE LOGITS

worthy

1.19

WORTH

0.85

ably

0.83

pads

0.73

worth

0.70

pad

0.69

able

0.66

 entanto

0.66

 carefully

0.64

worthiness

0.62

Activations Density 0.211%

notations or references that signify important information or observations

No Comments

No Known Activations