INDEX

Explanations

statements that suggest conclusions or inferences from previous information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

 gynhyrchwyd

-0.70

ForValue

-0.67

ValueGeneration

-0.65

 NavController

-0.65

تقاوى

-0.64

rungsseite

-0.63

</tfoot>

-0.61

UnusedPrivate

-0.60

 indisponible

-0.60

 ProtoMessage

-0.60

POSITIVE LOGITS

mentions

0.64

 Peninsula

0.63

 annoy

0.61

öglichkeiten

0.58

 imply

0.57

 Mentioned

0.57

RequestParam

0.56

Moe

0.54

(['/

0.54

 implies

0.54

Activations Density 0.062%

statements that suggest conclusions or inferences from previous information

No Comments

No Known Activations