INDEX

Explanations

key indicators and measurements related to the analysis and evaluation of concepts or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ISupport

-0.45

RTSC

-0.41

 صوتيه

-0.38

TB

-0.34

⅘

-0.34

endif

-0.33

此刻

-0.33

Sche

-0.33

Obituary

-0.33

CreateMap

-0.32

POSITIVE LOGITS

 important

0.65

 reasons

0.59

клопе

0.58

 ways

0.56

 reason

0.56

 factors

0.55

 facteurs

0.54

 belangrij

0.54

 interesting

0.53

 iNdEx

0.53

Activations Density 0.845%

key indicators and measurements related to the analysis and evaluation of concepts or systems

No Comments

No Known Activations