INDEX

Explanations

references to JSON objects and their structure in code

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

Code syntax with closing parentheses/brackets

np_acts-logits-general · gemini-2.0-flash

Json parsing code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Tikang

-0.54

ContentAlignment

-0.54

 Grá

-0.51

市镇

-0.50

tagHelper

-0.50

metheus

-0.48

 vira

-0.47

 owners

-0.47

cuadro

-0.47

IMPORTED

-0.46

POSITIVE LOGITS

IonicModule

0.65

MJ

0.61

 disambiguazione

0.60

JsonProperty

0.56

 Json

0.56

 betweenstory

0.56

tvguidetime

0.56

uspiel

0.55

 reconnaît

0.55

AndEndTag

0.55

Activations Density 0.178%

references to JSON objects and their structure in code

Code syntax with closing parentheses/brackets

Json parsing code

No Comments

No Known Activations