INDEX

Explanations

references to specific universities and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

SPATH

-0.61

 nakalista

-0.58

Scénario

-0.52

Ngb

-0.51

 arşivlendi

-0.51

 elseif

-0.50

ahalli

-0.49

 pory

-0.49

 BoxFit

-0.49

npm

-0.49

POSITIVE LOGITS

 iprot

0.76

 мәкал

0.66

amaño

0.66

FunctionFlags

0.63

WillAppear

0.58

 onAnimation

0.58

MLLoader

0.57

yakarta

0.56

 ComVisible

0.55

 IndexPath

0.54

Activations Density 0.445%

references to specific universities and locations

No Comments

No Known Activations

references to specific universities and locations

No Comments

No Known Activations