INDEX

Explanations

structured mathematical expressions or formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

PerformLayout

-0.72

Personendaten

-0.71

ViewFeatures

-0.67

WaitGroup

-0.67

kloped

-0.64

InputBorder

-0.61

 >=",

-0.60

OGND

-0.60

UnsafeEnabled

-0.60

 Paglinawan

-0.59

POSITIVE LOGITS

2.98

2.40

у

1.36

uu

1.18

𝑢

1.10

ｕ

1.10

ue

1.06

uw

1.06

 uLocal

1.03

uo

1.00

Activations Density 0.514%

structured mathematical expressions or formulas

No Comments

No Known Activations