INDEX

Explanations

syntax-related elements and structure in programming or technical documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ercises

-0.70

stretchr

-0.64

TagMode

-0.64

InputBorder

-0.63

 InputDecoration

-0.61

extAlignment

-0.61

ipheral

-0.59

UpInside

-0.56

ypal

-0.56

ponym

-0.56

POSITIVE LOGITS

<bos>

1.13

<",

0.79

AndEndTag

0.78

 nakalista

0.73

oa̍t

0.70

 propOrder

0.70

+#+#

0.69

 <=",

0.67

 jadx

0.67

 Roskov

0.67

Activations Density 0.730%

syntax-related elements and structure in programming or technical documents

No Comments

No Known Activations