INDEX

Explanations

code-related terms and structure, specifically in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ValueStyle

-1.27

tagHelperRunner

-1.17

__':

-1.05

 nahilalakip

-1.01

"}")

-0.94

 виправивши

-0.94

expandindo

-0.92

 propOrder

-0.91

\{\\

-0.90

TagHelpers

-0.88

POSITIVE LOGITS

0.94

”

0.89

",

0.68

''

0.65

";

0.62

0.61

」

0.58

</i>

0.58

");

0.58

")

0.58

Activations Density 1.495%

code-related terms and structure, specifically in a programming context

No Comments

No Known Activations