INDEX

Explanations

references to figures in scientific texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 ddelweddau

-0.58

 case

-0.57

Blu

-0.52

 ngân

-0.52

Blu

-0.52

bership

-0.50

addCriterion

-0.49

ligh

-0.49

otella

-0.49

CUB

-0.49

POSITIVE LOGITS

 umana

0.81

DoubleQuotes

0.80

gonic

0.78

WindowConstants

0.76

 surla

0.74

 SwitchCompat

0.72

Portale

0.68

Indented

0.68

 AssemblyProduct

0.68

mbic

0.67

Activations Density 0.166%

references to figures in scientific texts

No Comments

No Known Activations