INDEX

Explanations

corresponding mathematical or formatted expressions involving variables and constants

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

↵↵

-0.47

-0.45

-0.44

alige

-0.43

ìm

-0.42

-0.40

POSITIVE LOGITS

'{@

1.03

InjectAttribute

1.01

 NUKAT

1.00

ſelves

0.96

 Theſe

0.95

ſelf

0.90

adpleegd

0.89

كتشاف

0.88

 ſtate

0.87

 Diſ

0.87

Activations Density 0.642%

corresponding mathematical or formatted expressions involving variables and constants

No Comments

No Known Activations