INDEX

Explanations

terms related to memory components or functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

findpost

-1.00

EDEFAULT

-0.97

تقاوى

-0.89

]--;

-0.89

 propOrder

-0.88

 saites

-0.85

 خارجية

-0.84

 arşivlendi

-0.84

 TextInputType

-0.83

 ligiloj

-0.83

POSITIVE LOGITS

mem

1.37

mem

1.18

Mem

1.07

MEM

0.94

Mem

0.93

MEM

0.73

 Memes

0.67

httphttps

0.66

 aload

0.65

marginHorizontal

0.63

Activations Density 0.008%

terms related to memory components or functions

No Comments

No Known Activations