INDEX

Explanations

references to different methods or strategies for problem-solving

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Mur

-0.73

Mur

-0.71

 Crum

-0.68

tys

-0.67

ークル

-0.65

 Rosenberg

-0.62

 للمعارف

-0.61

 soldati

-0.61

 admiten

-0.60

 Munro

-0.59

POSITIVE LOGITS

 approaches

1.44

 Approaches

1.31

 APPROACH

1.27

Approach

1.26

 Approach

1.25

 approach

1.24

approach

1.10

Appro

1.03

 approached

1.01

 approaching

0.91

Activations Density 0.074%

references to different methods or strategies for problem-solving

No Comments

No Known Activations