INDEX

Explanations

words and phrases related to administrative processes and evidence in legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ArgsConstructor

-0.73

databind

-0.58

HasAnnotation

-0.56

setcounter

-0.54

Hochspringen

-0.54

していますが

-0.47

لیس

-0.47

lan

-0.47

 Administrativna

-0.47

 SwiftUI

-0.46

POSITIVE LOGITS

Autoritní

0.87

IndentedString

0.84

GEBURTSDATUM

0.83

parsedMessage

0.81

 समीक्षाओं

0.79

UnsafeEnabled

0.75

principalTable

0.74

Brainz

0.72

RegressionTest

0.72

AccessorTable

0.70

Activations Density 7.250%

words and phrases related to administrative processes and evidence in legal contexts

No Comments

No Known Activations