INDEX

Explanations

numerical and categorical data points related to specific entities or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

nodoc

-0.57

RectangleBorder

-0.55

crity

-0.53

")));

-0.52

:],

-0.51

__.__

-0.50

 لينك

-0.50

ImageContext

-0.49

 سكانية

-0.49

 StringTokenizer

-0.49

POSITIVE LOGITS

SourceChecksum

0.66

 specchio

0.60

InjectAttribute

0.58

 وتسجيلات

0.56

Források

0.55

NegativeButton

0.54

:✨

0.53

PositiveButton

0.53

WebpackPlugin

0.53

 calldata

0.52

Activations Density 0.647%

numerical and categorical data points related to specific entities or classifications

No Comments

No Known Activations