INDEX

Explanations

references to organizational or operational contexts, often pertaining to mathematical or statistical functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

RenderAtEndOf

-1.03

Diwedd

-0.87

CodeAttribute

-0.84

ransition

-0.78

FailureListener

-0.78

withIdentifier

-0.78

 useRef

-0.72

derry

-0.69

ciare

-0.69

zyden

-0.69

POSITIVE LOGITS

org

1.59

ORG

1.54

ORG

1.43

org

1.42

Org

1.33

Org

1.32

Organizations

1.00

 Jorg

1.00

 Morg

0.93

 Dorsey

0.90

Activations Density 0.057%

references to organizational or operational contexts, often pertaining to mathematical or statistical functionalities

No Comments

No Known Activations