INDEX

Explanations

mentions of hierarchical rankings or lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

AnchorStyles

-0.62

MemoryWarning

-0.56

StoreMessageInfo

-0.55

ograma

-0.51

 vulgaires

-0.49

ある

-0.48

laştır

-0.48

ಿಸ

-0.46

hysema

-0.45

 tranquille

-0.45

POSITIVE LOGITS

TOP

0.99

 Tops

0.96

notch

0.93

 notch

0.92

 tops

0.90

 tier

0.87

TOP

0.83

Top

0.81

getTop

0.81

 houſe

0.80

Activations Density 0.108%

mentions of hierarchical rankings or lists

No Comments

No Known Activations