INDEX

Explanations

mentions of a specific individual, likely in the context of an academic or scientific setting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

StructEnd

-0.54

AndEndTag

-0.50

 acetyl

-0.49

Wait

-0.47

ucchini

-0.47

BagLayout

-0.47

 Mind

-0.46

 kaarangay

-0.45

Mind

-0.45

찮

-0.43

POSITIVE LOGITS

 onData

0.77

0.69

@"/

0.65

 <=",

0.63

forName

0.61

^(@)

0.61

Ak

0.61

fony

0.60

adaptiveStyles

0.58

 toJson

0.58

Activations Density 0.066%

mentions of a specific individual, likely in the context of an academic or scientific setting

No Comments

No Known Activations