INDEX

Explanations

words related to booting processes or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Khas

-0.91

 للاسماء

-0.82

OMR

-0.79

PMC

-0.78

.*")]

-0.78

Samson

-0.76

 Nazar

-0.76

seamnă

-0.75

 Bary

-0.75

 esternos

-0.75

POSITIVE LOGITS

 boot

3.29

 Boot

3.06

boot

3.05

Boot

2.89

 BOOT

2.71

 boots

2.58

BOOT

2.47

boots

2.38

 Boots

2.24

Boots

2.11

Activations Density 0.038%

words related to booting processes or systems

No Comments

No Known Activations