INDEX

Explanations

geographic locations and directional indications

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 оригіналу

-0.45

LookAnd

-0.45

hyrchwyd

-0.45

expandindo

-0.44

setVerticalGroup

-0.42

 NSCoder

-0.42

tagHelperRunner

-0.42

entrySet

-0.40

SequentialGroup

-0.40

HomeAsUpEnabled

-0.39

POSITIVE LOGITS

pushFollow

0.49

 AssemblyProduct

0.47

nodoc

0.45

他們的

0.43

POI

0.42

 eorum

0.42

 descobri

0.41

Література

0.40

luß

0.40

Reprodução

0.39

Activations Density 0.012%

geographic locations and directional indications

No Comments

No Known Activations