INDEX

Explanations

phrases that inquire about definitions or explanations of terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

IntoConstraints

-0.71

ützen

-0.57

حوالہ

-0.56

 Audiodateien

-0.55

 transférez

-0.54

 BorderRadius

-0.54

 transfieras

-0.52

Composable

-0.52

 poisons

-0.52

 saites

-0.51

POSITIVE LOGITS

 connexes

0.66

########.

0.57

OGND

0.54

eroon

0.53

OPHER

0.52

:✨

0.52

substack

0.51

equalTo

0.49

flink

0.48

Diwedd

0.46

Activations Density 0.478%

phrases that inquire about definitions or explanations of terms and concepts

No Comments

No Known Activations