INDEX

Explanations

phrases indicating possession or existence related to subjects and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Synopsis

-0.54

<.

-0.50

NSYLVANIA

-0.50

jbl

-0.49

ervare

-0.48

олові

-0.48

теристи

-0.48

StringCopy

-0.47

ymal

-0.47

metri

-0.47

POSITIVE LOGITS

 BorderRadius

0.66

 always

0.65

webElementXpaths

0.64

migrationBuilder

0.63

ValueGeneration

0.62

few

0.60

تقاوى

0.59

 EconPapers

0.58

 already

0.58

 prouve

0.58

Activations Density 0.154%

phrases indicating possession or existence related to subjects and their actions

No Comments

No Known Activations