INDEX

Explanations

programming-related keywords or definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

enderror

-0.72

 Савезне

-0.67

 Regards

-0.64

 gynhyrchwyd

-0.63

+#+

-0.62

ĝis

-0.62

 blanches

-0.61

OfClass

-0.60

 EClass

-0.60

httphttps

-0.58

POSITIVE LOGITS

lat

0.75

TagHelper

0.73

voet

0.61

 records

0.60

yson

0.57

Rhestr

0.56

brunn

0.55

 recorded

0.54

__':

0.54

FileOutputStream

0.53

Activations Density 0.101%

programming-related keywords or definitions

No Comments

No Known Activations