INDEX

Explanations

symbols related to logical operations or conditions

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

 <=",

-0.73

 nakalista

-0.67

RegressionTest

-0.65

XmlAccessType

-0.62

 oração

-0.61

رشف

-0.60

 respeito

-0.59

 médicaux

-0.59

RTEE

-0.59

 Italijani

-0.58

POSITIVE LOGITS

||=

0.70

&&

0.67

PointerException

0.62

borderSide

0.62

bootstrapcdn

0.61

&&

0.61

omitempty

0.61

ENTI

0.59

rotu

0.58

tonsoft

0.58

Activations Density 0.039%

symbols related to logical operations or conditions

No Comments

No Known Activations