INDEX

Explanations

terms related to scientific analysis and measurement methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 prepared

-0.32

 forState

-0.31

prepared

-0.30

 TResult

-0.30

Gif

-0.29

 Prepared

-0.29

 nakalista

-0.29

 isSelected

-0.28

 ComVisible

-0.27

POSITIVE LOGITS

WithIOException

0.65

 estimation

0.60

 Estimation

0.60

rometry

0.58

 deduce

0.57

 estimate

0.57

 calibration

0.56

calibration

0.56

 Calibration

0.56

 determination

0.56

Activations Density 1.767%

terms related to scientific analysis and measurement methods

No Comments

No Known Activations