INDEX

Explanations

code-related documentation and comments specifically dealing with functions and their parameters

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

Code or programming-related text

np_acts-logits-general · gemini-2.0-flash

code comments and documentation

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

↵↵

-0.79

("}");

-0.64

-0.62

 EClass

-0.62

-0.60

<eos>

-0.60

car

-0.59

UnknownFieldSet

-0.58

ca

-0.57

POSITIVE LOGITS

//

0.79

///

0.68

0.67

Sucesor

0.67

 Escolar

0.66

0.65

 Pingback

0.65

[]:

0.65

 itſelf

0.64

didSet

0.63

Activations Density 0.027%

code-related documentation and comments specifically dealing with functions and their parameters

Code or programming-related text

code comments and documentation

No Comments

No Known Activations