INDEX

Explanations

definitions and descriptions related to terms and concepts

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

Token before colon or quotation mark

np_acts-logits-general · gemini-2.0-flash

numbers and specific terms

np_acts-logits-general · gemini-2.5-flash-lite

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

 myſelf

-1.46

 itſelf

-1.40

 raiſ

-1.35

 Anſ

-1.23

 himſelf

-1.22

Efq

-1.21

 Jefus

-1.18

 themſelves

-1.18

 iſt

-1.15

 Monfieur

-1.14

POSITIVE LOGITS

 micro

0.76

 meta

0.74

0.71

‘

0.70

“

0.69

0.68

con

0.64

 poly

0.63

di

0.63

dis

0.63

Activations Density 0.848%

definitions and descriptions related to terms and concepts

Token before colon or quotation mark

numbers and specific terms

No Comments

No Known Activations