INDEX

Explanations

elements related to structure or formatting in the text, including specialized vocabulary and document markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

tableFuture

-0.65

MLLoader

-0.60

 intptr

-0.55

MinWidth

-0.54

Happy

-0.50

happy

-0.50

cabul

-0.49

врат

-0.48

 ModelExpression

-0.48

 clic

-0.48

POSITIVE LOGITS

migrationBuilder

0.73

 ExecuteAsync

0.68

 Monfieur

0.68

XmlAccessType

0.66

 nakalista

0.65

 rhestr

0.65

EDEFAULT

0.64

 saites

0.64

 Jefus

0.63

 Majefty

0.63

Activations Density 0.389%

elements related to structure or formatting in the text, including specialized vocabulary and document markers

No Comments

No Known Activations