INDEX

Explanations

references to different seasons in a chronological context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Obrador

-0.86

ínű

-0.76

%)$

-0.76

luigi

-0.75

 Flücht

-0.74

 attent

-0.73

 Harlow

-0.73

 Montmartre

-0.72

 useDispatch

-0.72

ibatis

-0.72

POSITIVE LOGITS

 season

1.54

 seasons

1.52

 Seasons

1.45

 Season

1.43

Seasons

1.32

ASONS

1.32

Season

1.28

 SEASON

1.26

season

1.25

SEASON

1.11

Activations Density 0.043%

references to different seasons in a chronological context

No Comments

No Known Activations