INDEX

Explanations

technical jargon and terms related to programming or scientific contexts

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

 nakalista

-0.43

iset

-0.41

nalité

-0.37

 تضيفلها

-0.35

XIM

-0.35

PathParam

-0.35

gal

-0.35

chier

-0.34

som

-0.34

 sentimenti

-0.33

POSITIVE LOGITS

transQ

0.60

 وتسجيلات

0.58

 للاسماء

0.54

⟬

0.52

">//

0.52

 AssemblyProduct

0.52

 الحره

0.51

 Audiodateien

0.51

 NSCoder

0.51

TagMode

0.50

Activations Density 0.102%

technical jargon and terms related to programming or scientific contexts

No Comments

No Known Activations