INDEX

Explanations

names of authors and researchers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

MemoryWarning

-0.56

 himſelf

-0.53

ismer

-0.53

ustain

-0.51

 Jefus

-0.50

joel

-0.49

 isNameExpr

-0.49

zahn

-0.48

 raiſ

-0.48

ütfen

-0.48

POSITIVE LOGITS

 StatefulWidget

0.76

ThroughAttribute

0.72

 nakalista

0.71

CopyWith

0.68

 propOrder

0.66

 ddelweddau

0.63

+#+#

0.61

цездатний

0.59

ValueStyle

0.59

SourceChecksum

0.57

Activations Density 0.390%

names of authors and researchers

No Comments

No Known Activations