INDEX

Explanations

patterns related to numerical data and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 propOrder

-1.35

StoryboardSegue

-1.28

GEBURTSDATUM

-1.28

modelBuilder

-1.17

AndEndTag

-1.12

fromnode

-1.10

Хьажоргаш

-1.09

ConstraintMaker

-1.08

 tartalomajánló

-1.07

Билгалдахарш

-1.06

POSITIVE LOGITS

\{\\

0.42

 آم

0.40

⎨

0.40

͡

0.38

več

0.37

’

0.37

mł

0.37

kijken

0.36

 soft

0.34

<i>

0.34

Activations Density 0.056%

patterns related to numerical data and formatting

No Comments

No Known Activations