INDEX

Explanations

references to judges and judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 anti

-0.35

aid

-0.33

raisemb

-0.32

Története

-0.31

TargetApi

-0.30

newBuilder

-0.29

 Zusatz

-0.28

 élect

-0.28

 Utilizamos

-0.28

 Militär

-0.28

POSITIVE LOGITS

judge

0.75

 judge

0.74

UrlResolution

0.71

 <=",

0.71

Judge

0.69

 ſont

0.67

Jud

0.66

findpost

0.64

jud

0.64

 Judge

0.62

Activations Density 0.177%

references to judges and judgments

No Comments

No Known Activations