INDEX

Explanations

references to physical attributes, specifically height and weight measurements

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

bility

-0.50

 kele

-0.49

macs

-0.46

bile

-0.46

ttre

-0.45

addHandler

-0.45

 Øst

-0.44

ché

-0.43

 Technic

-0.43

πισ

-0.43

POSITIVE LOGITS

 tall

1.11

 height

1.07

 taller

1.03

Datuak

1.01

Tall

0.97

 Tall

0.96

tall

0.93

 tallest

0.93

 TALL

0.89

 Height

0.89

Activations Density 0.076%

references to physical attributes, specifically height and weight measurements

No Comments

No Known Activations