INDEX

Explanations

special formatting annotations, particularly those associated with documentation or metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

WriteBarrier

-0.55

extAlignment

-0.52

 Meksiku

-0.52

 الرياضيه

-0.49

UnusedPrivate

-0.49

StringTokenizer

-0.48

ImageContext

-0.48

parsedMessage

-0.45

ThroughAttribute

-0.44

fromCharCode

-0.44

POSITIVE LOGITS

param

0.81

__(/*!

0.67

return

0.65

thansa

0.64

noinspection

0.61

hatsu

0.58

ilidade

0.57

Param

0.56

 CreateTagHelper

0.56

 JAXB

0.55

Activations Density 0.039%

special formatting annotations, particularly those associated with documentation or metadata

No Comments

No Known Activations