INDEX

Explanations

references to lists or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 avenge

-0.54

phemy

-0.51

rapie

-0.50

nosis

-0.49

 informée

-0.49

issipp

-0.49

ètre

-0.49

="?

-0.48

脚注

-0.48

Beskrivelse

-0.48

POSITIVE LOGITS

 PyLong

0.65

등

0.64

 ExecuteAsync

0.63

richTextPanel

0.63

AccessorTable

0.59

 StatefulWidget

0.59

 CreateTagHelper

0.59

etc

0.59

 pinulongan

0.58

etc

0.58

Activations Density 0.269%

references to lists or examples

No Comments

No Known Activations