INDEX

Explanations

instances of the suffix "-able"

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

 surla

-0.60

__*/

-0.57

]='\

-0.52

 raiſ

-0.48

 HttpHeaders

-0.48

 userID

-0.47

Transkript

-0.47

 ſch

-0.47

*++

-0.47

 ſta

-0.47

POSITIVE LOGITS

UE

0.63

 Woods

0.59

ue

0.59

 woods

0.58

ificantly

0.50

 lift

0.49

mm

0.49

 brim

0.49

 ddelweddau

0.48

 masked

0.48

Activations Density 0.284%

instances of the suffix "-able"

No Known Activations