INDEX

Explanations

occurrences of "missing" and various forms of "reaction."

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 PLWABN

-0.70

MigrationBuilder

-0.66

økt

-0.62

Autoritní

-0.61

nanoTime

-0.59

 disponibilités

-0.58

usk

-0.58

UIControlState

-0.57

 pory

-0.55

FormState

-0.55

POSITIVE LOGITS

response

0.78

 reaction

0.75

 response

0.73

 betweenstory

0.69

Essentially

0.68

reaction

0.68

 basically

0.67

 misses

0.66

Reaction

0.66

 Basically

0.65

Activations Density 0.142%

occurrences of "missing" and various forms of "reaction."

No Comments

No Known Activations