INDEX

Explanations

instances of the term "pure" and related concepts

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

Negative Logits

WireFormatLite

-0.71

 dieß

-0.58

transQ

-0.55

madeus

-0.52

 república

-0.49

phrine

-0.47

 klaar

-0.47

 despatch

-0.46

ваку

-0.46

Stderr

-0.46

POSITIVE LOGITS

pure

0.75

 pure

0.73

 Pure

0.68

 Plain

0.63

 plain

0.60

 purely

0.57

Pure

0.57

Plain

0.56

 bless

0.54

 strictly

0.52

Activations Density 0.231%

instances of the term "pure" and related concepts

No Known Activations