INDEX

Explanations

specific technical terms and identifiers commonly found in formal and scientific contexts

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

ear, ea, learn

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 المعيارى

-0.60

WebElementEntity

-0.56

 nakalista

-0.55

 imageNamed

-0.48

 numberWith

-0.47

 iprot

-0.45

 Wiltshire

-0.45

 στιγ

-0.44

ılıyor

-0.44

istoitu

-0.44

POSITIVE LOGITS

ea

0.84

ead

0.84

eam

0.84

eak

0.84

ear

0.82

eah

0.79

eac

0.76

EA

0.76

lea

0.75

EAR

0.72

Activations Density 0.047%

specific technical terms and identifiers commonly found in formal and scientific contexts

ear, ea, learn

No Comments

No Known Activations