INDEX

Explanations

specific geographic locations and associated identifiers

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

locations followed by punctuation

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

 للمعارف

-0.45

 BoxFit

-0.45

 AssemblyCulture

-0.45

ябре

-0.44

icolon

-0.40

ACHUSET

-0.39

 VICTOR

-0.39

hex

-0.39

TagMode

-0.39

 Exacts

-0.38

POSITIVE LOGITS

 ProtoMessage

0.55

AccessorTable

0.49

Hochspringen

0.47

 bēr

0.47

moveToNext

0.45

Personendaten

0.44

QMetaType

0.44

rungsseite

0.43

 KeyError

0.42

 GenerationType

0.41

Activations Density 0.001%

specific geographic locations and associated identifiers

locations followed by punctuation

No Comments

No Known Activations