INDEX

Explanations

references to personal experiences and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eip

-0.63

 OMITBAD

-0.51

 senere

-0.51

 later

-0.50

Later

-0.46

čiau

-0.43

 afterwards

-0.42

 Later

-0.42

 successivamente

-0.42

 prosím

-0.42

POSITIVE LOGITS

SizeF

0.67

 gotta

0.64

probably

0.61

 IUser

0.61

 Certainly

0.61

 IndexPath

0.60

 виправивши

0.60

 larg

0.58

Might

0.58

 متعلقه

0.58

Activations Density 0.193%

references to personal experiences and decisions

No Comments

No Known Activations