INDEX

Explanations

code-related syntax or elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

TextAlign

-0.65

Geplaatst

-0.58

addGap

-0.57

 latter

-0.52

WhereInput

-0.50

Бахар

-0.49

↵↵

-0.49

 considération

-0.48

 Савез

-0.48

localctx

-0.48

POSITIVE LOGITS

tagHelperRunner

0.84

 myſelf

0.77

 Monfieur

0.75

 iſt

0.72

Efq

0.70

 Theſe

0.70

^(@)

0.69

 itſelf

0.69

ſelf

0.66

mPaint

0.65

Activations Density 0.199%

code-related syntax or elements

No Comments

No Known Activations