INDEX

Explanations

phrases indicating purpose or reasoning, particularly related to clarity and simplicity in explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

principalColumn

-0.75

 StatelessWidget

-0.64

 Baillargeon

-0.63

ResumeLayout

-0.61

 GenerationType

-0.61

šinou

-0.59

 مشين

-0.59

URLException

-0.58

TintMode

-0.57

parsedMessage

-0.56

POSITIVE LOGITS

 simplicity

1.41

 convenience

1.25

 clarity

1.15

 ease

1.08

 brevity

1.06

 easier

1.03

convenience

0.93

 sake

0.93

 simplification

0.91

 completeness

0.88

Activations Density 0.479%

phrases indicating purpose or reasoning, particularly related to clarity and simplicity in explanations

No Comments

No Known Activations