INDEX

Explanations

elements related to legal proceedings and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zionalità

-0.55

šanu

-0.54

lujah

-0.53

InjectAttribute

-0.50

UVWXYZ

-0.50

BIBLIO

-0.49

NOWLEDGE

-0.49

amental

-0.48

lesson

-0.48

 siyang

-0.47

POSITIVE LOGITS

 Roskov

0.62

OGND

0.62

 gynhyrchwyd

0.58

PreferredItem

0.53

WarningLevel

0.51

GEBURTSDATUM

0.51

揄

0.50

Становништво

0.49

 voren

0.47

IActionResult

0.47

Activations Density 0.528%

elements related to legal proceedings and documentation

No Comments

No Known Activations