INDEX

Explanations

various expressions related to methods or approaches

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

 ―――――

-1.15

 Monfieur

-1.13

Datuak

-1.10

 pleaſure

-1.08

вгений

-1.08

 Majefty

-1.08

 Theſe

-1.06

 Anſ

-1.05

 preſent

-1.05

 Reſ

-1.04

POSITIVE LOGITS

way

2.40

Way

2.36

WAY

2.26

Way

2.19

way

2.08

WAY

1.88

 ways

1.88

 Ways

1.73

 WAYS

1.65

Ways

1.62

Activations Density 0.071%

various expressions related to methods or approaches

No Comments

No Known Activations