INDEX

Explanations

numerical values and their formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Савезне

-1.43

Autoritní

-1.38

 betweenstory

-1.37

RegressionTest

-1.36

 myſelf

-1.33

LookAnd

-1.33

expandindo

-1.30

 autorytatywna

-1.28

ArrowToggle

-1.28

 كومونز

-1.25

POSITIVE LOGITS

↵↵

1.05

0.93

↵

0.87

↵↵↵↵

0.80

<eos>

0.79

0.77

and

0.77

0.74

<strong>

0.72

↵↵↵

0.71

Activations Density 0.124%

numerical values and their formatting

No Comments

No Known Activations