INDEX

Explanations

quantitative data related to physical health assessments and training routines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

DropColumn

-0.61

])->

-0.50

))->

-0.49

RUnlock

-0.48

(__('

-0.48

createComponent

-0.48

ações

-0.47

styleUrls

-0.47

__))

-0.46

縁

-0.46

POSITIVE LOGITS

 exercises

0.93

 intensity

0.90

 workouts

0.87

 workout

0.86

 Intensity

0.82

intensity

0.81

Intensity

0.81

 intervals

0.77

 cardio

0.77

 interval

0.75

Activations Density 0.213%

quantitative data related to physical health assessments and training routines

No Comments

No Known Activations