INDEX

Explanations

phrases expressing justifications or reasons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

TestTools

-0.68

httphttps

-0.67

finally

-0.67

 للمعارف

-0.66

 समीक्षक

-0.65

 rare

-0.64

 bezeichneter

-0.60

alot

-0.59

 raras

-0.58

 rarity

-0.57

POSITIVE LOGITS

Pourquoi

0.59

makeConstraints

0.59

Why

0.56

])));

0.55

mazan

0.54

why

0.54

Why

0.52

ConstraintMaker

0.50

Reasons

0.50

Proč

0.49

Activations Density 0.194%

phrases expressing justifications or reasons

No Comments

No Known Activations