INDEX

Explanations

phrases indicating quantity or magnitude, particularly those suggesting "more" or "less"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

 الرياضيه

-0.52

ihnachten

-0.43

最快更新

-0.42

 intptr

-0.42

 שוליים

-0.41

ьажоргаш

-0.41

 defaultstate

-0.40

 solche

-0.40

adaptiveStyles

-0.40

consulté

-0.38

POSITIVE LOGITS

DataSnapshot

0.45

 elif

0.44

 destructor

0.43

 "..\..\..\

0.43

 skippy

0.43

OrNil

0.42

рецепт

0.42

seteq

0.42

TokenNameLBRACE

0.42

CodeAttribute

0.41

Activations Density 0.773%

phrases indicating quantity or magnitude, particularly those suggesting "more" or "less"

No Comments

No Known Activations