INDEX

Explanations

actions related to communication and expression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

花板

-0.59

WriteAttribute

-0.57

glLoadIdentity

-0.55

EndContext

-0.54

</

-0.52

Filmographie

-0.51

InstrumentedTest

-0.51

клопе

-0.50

PageRoute

-0.49

NSNotification

-0.49

POSITIVE LOGITS

 AssemblyCulture

0.66

principalTable

0.65

 béné

0.60

easier

0.58

 coraz

0.58

 Wicidata

0.57

GOTREF

0.57

 abusing

0.56

 parlant

0.56

 autorité

0.56

Activations Density 0.190%

actions related to communication and expression

No Comments

No Known Activations