INDEX

Explanations

occurrences of the term "net" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Rhestr

-0.57

NOPQRST

-0.54

 dolci

-0.52

GFX

-0.52

 maravilla

-0.50

╕

-0.50

toBeTruthy

-0.50

 quotidi

-0.50

 schen

-0.50

 Thom

-0.49

POSITIVE LOGITS

net

1.31

 nets

1.19

Net

0.91

 cage

0.90

jar

0.90

nets

0.84

 static

0.81

net

0.80

 Nets

0.76

cage

0.73

Activations Density 0.073%

occurrences of the term "net" in various contexts

No Comments

No Known Activations