INDEX

Explanations

statistical comparisons and ratios involving numerical data

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

TR

-0.43

oral

-0.43

lem

-0.43

$\{

-0.41

ਚ

-0.41

LE

-0.38

 internal

-0.38

$[

-0.38

ňa

-0.38

$\

-0.38

POSITIVE LOGITS

InjectAttribute

1.13

 nakalista

1.07

ValueStyle

1.05

GEBURTSDATUM

1.03

 <=",

0.91

writerow

0.89

UnusedPrivate

0.88

IsContent

0.86

parsedMessage

0.85

styleType

0.84

Activations Density 1.162%

statistical comparisons and ratios involving numerical data

No Comments

No Known Activations