INDEX

Explanations

statements related to the length or size of data structures

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

Code, math, or database related tokens

np_acts-logits-general · gemini-2.0-flash

comparison operators and counts

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 صوتيه

-0.88

windowFixed

-0.85

Geplaatst

-0.78

存于互联网档案馆

-0.78

 lenker

-0.72

 المعيارى

-0.70

AddTagHelper

-0.67

sizeCache

-0.67

الحياه

-0.67

 nahilalakip

-0.65

POSITIVE LOGITS

1.10

0.90

<=

0.82

0.73

()>

0.73

<=

0.72

$>

0.71

']>

0.71

==

0.66

)>

0.66

Activations Density 0.084%

statements related to the length or size of data structures

Code, math, or database related tokens

comparison operators and counts

No Comments

No Known Activations