INDEX

Explanations

references to the word "given" indicating context or premise

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

 itſelf

-1.21

 themſelves

-1.17

 himſelf

-1.16

 Monfieur

-1.06

 myſelf

-1.06

 houſe

-1.02

 Houſe

-0.98

 whoſe

-0.96

 Jefus

-0.96

 leaſt

-0.95

POSITIVE LOGITS

0.56

 Given

0.55

0.54

ness

0.53

ra

0.51

esen

0.50

by

0.50

how

0.50

Given

0.50

van

0.49

Activations Density 0.115%

references to the word "given" indicating context or premise

No Comments

No Known Activations