INDEX

Explanations

phrases indicating evidence or criteria related to legal assertions or claims

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

that followed by pronoun or determiner

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 when

-0.44

if

-0.41

 since

-0.41

ToTop

-0.41

-0.40

Since

-0.35

For

-0.34

 while

-0.33

 Since

-0.33

 whenever

-0.33

POSITIVE LOGITS

 AssemblyCulture

0.63

VersionUID

0.62

########.

0.62

majánló

0.62

BufferException

0.60

ésultats

0.59

 noDo

0.57

ðsíða

0.57

 betweenstory

0.56

 geſch

0.56

Activations Density 0.110%

phrases indicating evidence or criteria related to legal assertions or claims

that followed by pronoun or determiner

No Comments

No Known Activations