INDEX

Explanations

code snippets and formatting elements related to data representation

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

gatsby

-0.69

↴

-0.63

بوابة

-0.63

 mxArray

-0.60

endcsname

-0.59

 odkazy

-0.59

Nuorodos

-0.57

pyplot

-0.57

fromCharCode

-0.57

 havoc

-0.57

POSITIVE LOGITS

Personensuche

0.70

 оригіналу

0.70

0.67

ngdoc

0.65

 propOrder

0.64

qquad

0.64

0.62

 tasche

0.61

parsedMessage

0.60

Activations Density 0.216%

code snippets and formatting elements related to data representation

No Comments

No Known Activations