INDEX

Explanations

structure and syntax of code, particularly focusing on function definitions and class methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SequentialGroup

-0.60

はじめに

-0.59

rxjs

-0.59

 binh

-0.58

providedIn

-0.55

 then

-0.53

èdia

-0.53

bių

-0.53

ponses

-0.52

 infatti

-0.51

POSITIVE LOGITS

endmodule

0.67

NUMX

0.59

cerely

0.56

"}";

0.54

󠁢

0.53

})();

0.52

CloseOperation

0.51

MigrationBuilder

0.51

ousands

0.51

Activations Density 0.130%

structure and syntax of code, particularly focusing on function definitions and class methods

No Comments

No Known Activations