INDEX

Explanations

keywords related to programming constructs and API interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 &___

-0.77

ագրություններ

-0.69

Jeografia

-0.67

Rüyada

-0.61

locator

-0.59

DebuggerStep

-0.58

IVEREF

-0.56

ApiProperty

-0.55

adze

-0.55

lasty

-0.54

POSITIVE LOGITS

Override

0.82

NUMX

0.69

override

0.67

 Majefty

0.67

^(@)

0.65

 CreateTagHelper

0.64

\{\\

0.62

 overridden

0.58

ODS

0.56

 override

0.52

Activations Density 0.022%

keywords related to programming constructs and API interactions

No Comments

No Known Activations