INDEX

Explanations

occurrences of the word "jump"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 NSCoder

-0.69

StandardCharsets

-0.59

تقاوى

-0.57

Tembelea

-0.56

 dourada

-0.53

 Dacia

-0.52

BeginContext

-0.50

 AssemblyCompany

-0.50

ล้ว

-0.50

 怎样

-0.50

POSITIVE LOGITS

 jump

4.68

 Jump

4.17

jump

4.13

Jump

3.93

 jumps

3.91

 jumping

3.87

 jumped

3.79

 JUMP

3.75

jumping

3.42

 Jumping

3.37

Activations Density 0.053%

occurrences of the word "jump"

No Comments

No Known Activations