INDEX

Explanations

calls to log or alert functions in a code context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

einander

-0.59

 intptr

-0.59

 raiſ

-0.53

⁀

-0.53

itespace

-0.52

zyb

-0.51

 تكبرها

-0.50

ждый

-0.49

bbage

-0.49

 Völker

-0.49

POSITIVE LOGITS

println

0.72

 متعلقه

0.69

 cref

0.63

 BorderSide

0.60

endl

0.59

GOTREF

0.58

VersionUID

0.58

Println

0.58

 bunk

0.58

mesg

0.57

Activations Density 0.019%

calls to log or alert functions in a code context

No Comments

No Known Activations