INDEX

Explanations

terms related to weight and weight changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

✨:

-0.99

 nahilalakip

-0.91

omiast

-0.91

 mitosis

-0.88

 hostels

-0.87

expandindo

-0.87

 bambú

-0.86

OGND

-0.84

Mij

-0.83

 näin

-0.83

POSITIVE LOGITS

 weight

1.70

weight

1.67

 Weight

1.66

 weights

1.64

weights

1.57

 WEIGHT

1.54

Weight

1.45

WEIGHT

1.41

 Weights

1.32

 weighting

1.19

Activations Density 0.078%

terms related to weight and weight changes

No Comments

No Known Activations