INDEX

Explanations

components and features related to automotive design and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

EDEFAULT

-0.50

gpl

-0.49

حياته

-0.49

 للمعارف

-0.47

haltens

-0.45

 hồng

-0.45

 geda

-0.45

kina

-0.44

ertos

-0.44

oredCriteria

-0.44

POSITIVE LOGITS

 wheels

1.04

 rims

1.03

 wheel

0.96

rim

0.91

 alloy

0.90

 spoke

0.90

spoke

0.87

 Wheels

0.85

 alloys

0.83

 spokes

0.82

Activations Density 0.101%

components and features related to automotive design and performance

No Comments

No Known Activations