INDEX

Explanations

specific nouns related to technical and scientific subjects

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ویکی‌پدی

-0.79

matchCondition

-0.79

adaptiveStyles

-0.77

 kasarigan

-0.67

 Roskov

-0.65

bootstrapcdn

-0.64

 >=",

-0.64

 للمعارف

-0.63

SourceChecksum

-0.61

 transfieras

-0.60

POSITIVE LOGITS

уда

0.36

ry

0.35

 Olympia

0.33

ruh

0.33

୧

0.33

=”

0.32

alp

0.32

yay

0.32

saco

0.32

ube

0.32

Activations Density 0.250%

specific nouns related to technical and scientific subjects

No Comments

No Known Activations