INDEX

Explanations

text related to reader engagement and immersion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

excellents

-0.59

 rêves

-0.55

asticity

-0.52

brainly

-0.51

Require

-0.51

 originaux

-0.50

FormTagHelper

-0.49

 leçons

-0.48

 personnelle

-0.48

 blocco

-0.48

POSITIVE LOGITS

Tracce

0.73

הערות

0.60

 مرئيه

0.60

ьому

0.59

WithIOException

0.57

 تانيه

0.56

)_/¯

0.55

Jegyzetek

0.54

 الاطلاع

0.54

êques

0.54

Activations Density 0.323%

text related to reader engagement and immersion

No Comments

No Known Activations