INDEX

Explanations

phrases and words that indicate actions, occurrences, and relational dynamics over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

iliki

-0.53

 majeure

-0.50

SPONSORED

-0.49

rxjs

-0.48

NewUrlParser

-0.47

 miễn

-0.46

!*\

-0.46

'{@

-0.45

illir

-0.45

 AssemblyVersion

-0.44

POSITIVE LOGITS

ItemBackground

0.68

 discussing

0.60

 preparing

0.59

SourceChecksum

0.59

 kasarigan

0.58

 sedang

0.56

 talking

0.56

 parlando

0.55

 samband

0.55

 المعرف

0.54

Activations Density 0.222%

phrases and words that indicate actions, occurrences, and relational dynamics over time

No Comments

No Known Activations