INDEX

Explanations

elements related to instructions, usage, and functionality of applications or software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

:+:

-0.82

脚注の使い方

-0.77

 Walkover

-0.73

 Савезне

-0.73

SourceChecksum

-0.71

setVerticalGroup

-0.68

 stanovnika

-0.68

ksesta

-0.67

oredCriteria

-0.67

protoimpl

-0.66

POSITIVE LOGITS

hring

0.49

0.47

ﬁ

0.44

↵↵

0.43

\\

0.43

ific

0.41

â

0.40

GetAsync

0.40

 inter

0.39

ni

0.39

Activations Density 1.566%

elements related to instructions, usage, and functionality of applications or software

No Comments

No Known Activations