INDEX

Explanations

structured data or specific patterns within texts, particularly in technical or scientific contexts

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

 Halen

-0.57

 Camara

-0.56

 وع

-0.53

 Healey

-0.51

Leb

-0.49

 Hannover

-0.48

xico

-0.48

 Dudley

-0.48

 Gara

-0.48

 Clayton

-0.48

POSITIVE LOGITS

 تضيفلها

1.51

findpost

1.25

RenderAtEndOf

1.10

########.

1.06

Autoritní

1.01

 EconPapers

0.94

 ErrIntOverflow

0.94

setVerticalGroup

0.93

IsContent

0.93

DoubleQuotes

0.88

Activations Density 0.071%

structured data or specific patterns within texts, particularly in technical or scientific contexts

No Comments

No Known Activations