INDEX

Explanations

code-related functions and recursive calls

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

Code snippets or code-related terms

np_acts-logits-general · gemini-2.0-flash

programming keywords and code constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

DataSnapshot

-0.70

+#+

-0.67

 مُعرِّف

-0.54

UnusedPrivate

-0.53

__).

-0.52

popularity

-0.50

writeFieldEnd

-0.49

NameInMap

-0.49

PendingIntent

-0.49

%")

-0.48

POSITIVE LOGITS

 ujednoznacz

0.61

kozás

0.61

 ProductService

0.59

 fallu

0.59

出版年

0.57

 judiciaire

0.57

 présidentielle

0.54

 recursively

0.54

ductors

0.53

 tributaries

0.53

Activations Density 0.124%

code-related functions and recursive calls

Code snippets or code-related terms

programming keywords and code constructs

No Comments

No Known Activations