INDEX

Explanations

numbers and numerical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.99

es

-0.81

-0.78

-0.74

-0.73

-0.71

-0.70

-0.68

os

-0.65

POSITIVE LOGITS

 ſeveral

1.40

 itſelf

1.36

 themſelves

1.36

 purpoſe

1.34

ſelves

1.34

 ſmall

1.32

ſelf

1.32

 himſelf

1.32

 againſt

1.30

 reaſon

1.30

Activations Density 0.092%

numbers and numerical expressions

No Comments

No Known Activations