INDEX

Explanations

unique identifiers or keywords related to specific classifications or categories

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

next to

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 Houſe

-0.64

 myſelf

-0.58

 Majefty

-0.57

 Romains

-0.54

 Monfieur

-0.52

 ſta

-0.50

 houſe

-0.49

Efq

-0.49

 ſeveral

-0.49

Eſ

-0.48

POSITIVE LOGITS

MENAFN

0.76

 ویکی‌پدی

0.62

PreferredItem

0.49

цездатний

0.48

calça

0.45

 vPvB

0.45

Fprintf

0.45

ﬅ

0.45

writeFieldEnd

0.45

XmlType

0.45

Activations Density 0.101%

unique identifiers or keywords related to specific classifications or categories

next to

No Comments

No Known Activations