INDEX

Explanations

phrases indicating significant losses or defeats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

+#+#

-0.63

 الرياضيه

-0.60

AnchorTagHelper

-0.55

 AssemblyCulture

-0.54

writeFieldEnd

-0.52

RegressionTest

-0.49

rrggbb

-0.48

 secours

-0.48

 srdce

-0.47

 atmósfera

-0.46

POSITIVE LOGITS

 easy

0.53

 overwhelming

0.51

 domination

0.48

easy

0.48

 overkill

0.47

 blowout

0.46

 effortless

0.46

 annihil

0.45

 overwhelmingly

0.44

 facile

0.44

Activations Density 0.576%

phrases indicating significant losses or defeats

No Comments

No Known Activations