INDEX

Explanations

references to legs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

hasMoreElements

-0.48

awaiter

-0.41

shadowOpacity

-0.35

ForResult

-0.35

ChildScrollView

-0.35

FirstResponder

-0.34

 Plage

-0.33

paramMap

-0.33

 interac

-0.32

 AssemblyVersion

-0.32

POSITIVE LOGITS

:✨

0.91

OGND

0.66

leg

0.65

 tiered

0.64

 Gesture

0.63

 stamp

0.60

 concession

0.60

principles

0.59

Tier

0.59

entiment

0.58

Activations Density 1.929%

references to legs

No Comments

No Known Activations