INDEX

Explanations

expressions related to criticism or explanations of concepts

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

setVerticalGroup

-0.85

 виправивши

-0.69

rrggbb

-0.66

 мәкал

-0.64

 Poincar

-0.58

eterangan

-0.57

-0.56

autorest

-0.56

 snippetHide

-0.55

 myſelf

-0.55

POSITIVE LOGITS

focusable

0.51

原始内容存档

0.51

Tri

0.46

 שוליים

0.46

ことです

0.45

ofia

0.44

üme

0.43

tri

0.43

 velkommen

0.43

不大

0.43

Activations Density 0.376%

expressions related to criticism or explanations of concepts

No Comments

No Known Activations