INDEX

Explanations

mention of various aspects or features related to a topic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

XtraGrid

-0.80

lectricité

-0.75

MemoryWarning

-0.72

 bones

-0.71

bones

-0.69

assium

-0.69

blå

-0.67

InputBorder

-0.67

TUM

-0.66

 szív

-0.66

POSITIVE LOGITS

 Aspects

1.54

 aspects

1.51

 Aspect

1.47

Aspects

1.46

aspects

1.43

 aspect

1.43

 ASPECTS

1.41

Aspect

1.39

aspect

1.23

 aspec

1.14

Activations Density 0.054%

mention of various aspects or features related to a topic

No Comments

No Known Activations