INDEX

Explanations

terms indicating standards, norms, or common practices

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

and

-0.49

près

-0.46

membre

-0.45

idać

-0.45

 köt

-0.44

 vannak

-0.43

 nennt

-0.41

Bukan

-0.40

pieza

-0.40

Dữ

-0.39

POSITIVE LOGITS

rungsseite

0.92

yntaxException

0.83

dafx

0.83

脚注の使い方

0.80

 dagens

0.77

 MainAxisSize

0.77

Viited

0.76

PHeader

0.75

ⓘ

0.74

DropColumn

0.74

Activations Density 0.332%

terms indicating standards, norms, or common practices

No Comments

No Known Activations