INDEX

Explanations

references to data and numerical comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UTIVE

-0.60

himu

-0.58

########.

-0.57

jsdelivr

-0.57

IENTE

-0.57

ftagPool

-0.56

lared

-0.56

 Vance

-0.55

ABETH

-0.55

zenberg

-0.55

POSITIVE LOGITS

InjectAttribute

0.72

 JADX

0.64

تقاوى

0.56

]")]

0.55

richTextPanel

0.52

RenderAtEndOf

0.50

contentLoaded

0.50

Composable

0.49

 Audiodateien

0.49

الدراسه

0.48

Activations Density 1.079%

references to data and numerical comparisons

No Comments

No Known Activations