INDEX

Explanations

references to "paragraph" structures or sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Roskov

-0.97

Sucesor

-0.92

 wireType

-0.92

/>";

-0.92

SpringBootTest

-0.90

ſelf

-0.90

 useEffect

-0.86

")->

-0.85

 متعلقه

-0.84

;">

-0.84

POSITIVE LOGITS

par

2.13

Par

1.96

Par

1.96

par

1.96

PAR

1.90

PAR

1.78

 Paro

1.39

 Parr

1.35

 pars

1.33

 Parrish

1.33

Activations Density 0.045%

references to "paragraph" structures or sections

No Comments

No Known Activations