INDEX

Explanations

references to roles, positions, or highlighted concepts in a document

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

"as" followed by "the"

np_acts-logits-general · gemini-2.0-flash

as the definition

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

unar

-0.47

 Reverso

-0.44

rels

-0.42

 toca

-0.40

 συμβ

-0.39

 girasol

-0.39

由

-0.39

外部連結

-0.37

tav

-0.36

sind

-0.36

POSITIVE LOGITS

ScopeManager

0.84

 &___

0.75

 CanadaChoose

0.66

URLException

0.65

URUS

0.64

ErrUnexpectedEOF

0.64

AndEndTag

0.64

HostException

0.63

 NUKAT

0.63

rrggbb

0.62

Activations Density 0.314%

references to roles, positions, or highlighted concepts in a document

"as" followed by "the"

as the definition

No Comments

No Known Activations