INDEX

Explanations

content related to specific product recommendations and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 protoimpl

-0.77

afficheront

-0.76



-0.69

تفصیلات

-0.66

Personensuche

-0.65

 spalle

-0.61

WebElementEntity

-0.60

قایناق‌لار

-0.59

Архівовано

-0.59

 ErrIntOverflow

-0.59

POSITIVE LOGITS

itäts

0.54

יש

0.53

ok

0.52

 bagus

0.51

 online

0.51

 handle

0.51

 kalau

0.50

 Ditto

0.50

FTS

0.49

Activations Density 0.444%

content related to specific product recommendations and experiences

No Comments

No Known Activations