INDEX

Explanations

the use of auxiliary verbs such as, will, was, should, are, and similar words

oai_token-act-pair · gemini-2.0-flash

fight

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵↵

-3.38

↵

-2.61

<eos>

-2.42

↵↵↵

-1.91

↵↵↵↵

-1.80

↵↵↵↵↵

-1.57

↵↵↵↵↵↵

-1.55

↵↵↵↵↵↵↵↵

-1.45

↵↵↵↵↵↵↵

-1.45

...

-1.37

POSITIVE LOGITS

 BorderSide

0.54

 }}$}

0.54

}(\

0.54

囗

0.49

 createSprite

0.48

}(

0.48

>(_

0.44

tagHelperRunner

0.43

}{

0.43

']->

0.42

Activations Density 6.226%

the use of auxiliary verbs such as, will, was, should, are, and similar words

fight

No Comments

No Known Activations