INDEX

Explanations

phrases and words indicating proximity or closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

hagy

-0.51

 yoksa

-0.47

ดย

-0.47

baga

-0.44

 waveform

-0.44

LayoutManager

-0.44

 Purpose

-0.43

oftware

-0.43

目的

-0.42

 đoàn

-0.41

POSITIVE LOGITS

 proximity

1.23

awtextra

1.00

 Proximity

0.98

ximity

0.96

Proximity

0.95

 closeness

0.94

closer

0.93

 NEAR

0.88

IntoConstraints

0.88

 approximation

0.87

Activations Density 0.229%

phrases and words indicating proximity or closeness

No Comments

No Known Activations