INDEX

Explanations

technical terms related to devices and their functionalities

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

Chham

-0.63

цездатний

-0.57

 investments

-0.49

Portail

-0.49

chenkt

-0.48

invest

-0.47

 సౌకర్య

-0.47

Linker

-0.47

RegressionTest

-0.46

funded

-0.45

POSITIVE LOGITS

 signals

0.98

 signal

0.92

 transmitted

0.87

 processed

0.78

 decoded

0.76

signals

0.76

 feeds

0.76

 feed

0.75

 relayed

0.74

信号

0.73

Activations Density 1.245%

technical terms related to devices and their functionalities

No Comments

No Known Activations