INDEX

Explanations

legal terminology and phrases related to court cases and judicial processes

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

numeric citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 invokingState

-0.79

 CreateTagHelper

-0.57

 mergeFrom

-0.53

 estekak

-0.52

addContainerGap

-0.52

prüche

-0.51

----</

-0.51

WithIOException

-0.50

ніципалі

-0.50

OGND

-0.49

POSITIVE LOGITS

Actually

0.60

 Actually

0.60

See

0.57

See

0.55

 actually

0.54

 aslında

0.54

↩

0.53

 Presumably

0.49

Note

0.48

actually

0.48

Activations Density 0.123%

legal terminology and phrases related to court cases and judicial processes

numeric citations

No Comments

No Known Activations