INDEX

Explanations

statistical significance and relationships in research data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

หน

-0.48

antd

-0.41

 spé

-0.41

Node

-0.39

orex

-0.39

dyr

-0.38

 goma

-0.37

 rege

-0.37

multirow

-0.37

 usan

-0.37

POSITIVE LOGITS

 snippetHide

0.97

 MainAxisSize

0.94

脚注の使い方

0.90

SharedDtor

0.90

SourceChecksum

0.86

 Paglinawan

0.84

TagMode

0.82

Бахар

0.81

DockStyle

0.79

 GenerationType

0.79

Activations Density 0.435%

statistical significance and relationships in research data

No Comments

No Known Activations