INDEX

Explanations

specific formatting or structure associated with medical or technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ectoria

-0.65

 validamos

-0.55

-0.51

bukkit

-0.49

microb

-0.48

Identyfik

-0.48

abank

-0.48

bcryptjs

-0.47

cování

-0.47

Mer

-0.47

POSITIVE LOGITS

 EconPapers

0.66

])).

0.66

Véxase

0.66

 unknownFields

0.64

 réglable

0.62

.$_

0.61

 оригіналу

0.61

contentPane

0.60

 Drapeau

0.60

 Fiske

0.60

Activations Density 0.028%

specific formatting or structure associated with medical or technical documentation

No Comments

No Known Activations