INDEX

Explanations

terms related to advantages and benefits

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

.*")]

-0.59

versiti

-0.51

 Winaray

-0.51

 fired

-0.51

ichord

-0.48

 relâche

-0.48

 utafitiHapana

-0.48

 ujednoznacz

-0.48

cils

-0.47

➟

-0.47

POSITIVE LOGITS

 accrue

1.05

 accruing

1.02

 gained

0.97

 accrued

0.91

 accru

0.82

 realized

0.81

 achieved

0.80

 derived

0.80

 enjoyed

0.78

 obtained

0.73

Activations Density 0.355%

terms related to advantages and benefits

No Comments

No Known Activations