INDEX

Explanations

specific numerical or quantitative information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 kaarangay

-0.60

for

-0.54

 eventdata

-0.53

 ModelAndView

-0.52

및

-0.51

់

-0.47

toward

-0.47

bonjour

-0.47

ècie

-0.47

Std

-0.47

POSITIVE LOGITS

 Those

0.81

 Many

0.81

Additionally

0.80

Those

0.80

 Additionally

0.79

These

0.79

 There

0.79

They

0.79

 They

0.78

There

0.78

Activations Density 0.069%

specific numerical or quantitative information

No Comments

No Known Activations