INDEX

Explanations

terms related to programming variables and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

SharedDtor

-0.94

LookAnd

-0.92

 CreateTagHelper

-0.83

makeText

-0.76



-0.75

windowFixed

-0.75

انجليز

-0.75

 мәкал

-0.74

Diweddarwch

-0.74

ConstraintMaker

-0.72

POSITIVE LOGITS

 purpoſe

0.74

 ſtate

0.69

ſelf

0.66

 Venedig

0.66

 cauſe

0.65

 original

0.65

mein

0.64

 mevcut

0.64

 houſe

0.63

 reaſon

0.62

Activations Density 0.073%

terms related to programming variables and references

No Comments

No Known Activations