INDEX

Explanations

comparative phrases and structures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 RSSSF

-0.98

 ―――――

-0.86

 myſelf

-0.83

 ་་

-0.80

 whoſe

-0.79

 raiſ

-0.78

 unſ

-0.78

melons

-0.77

 Perſ

-0.77

 greateſt

-0.76

POSITIVE LOGITS

 those

0.72

the

0.71

 quelli

0.62

 like

0.60

 what

0.56

回し

0.56

 quello

0.56

 here

0.55

sigs

0.55

 celui

0.55

Activations Density 0.330%

comparative phrases and structures

No Comments

No Known Activations