INDEX

Explanations

references to significant historical events or figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

:✨

-0.80

 comigo

-0.72

CppMethod

-0.70

 Sarm

-0.67

migrationBuilder

-0.66

VHS

-0.64

 eighties

-0.64

AndEndTag

-0.64

 anhydride

-0.61

utsal

-0.61

POSITIVE LOGITS

sizeCache

0.57

WebElementEntity

0.53

 Beat

0.49

 fifties

0.48

Eisen

0.45

vair

0.45

 doPost

0.45

 Eisenhower

0.43

SourceChecksum

0.41

 Korean

0.41

Activations Density 0.365%

references to significant historical events or figures

No Comments

No Known Activations