INDEX

Explanations

phrases indicating exceptions or exclusions

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

gatsby

-0.64

 famí

-0.61

 AssemblyCompany

-0.59

PreInfinity

-0.57

̀ng

-0.57

-0.56

TintMode

-0.56

GOTREF

-0.56

DispatchToProps

-0.56

-0.54

POSITIVE LOGITS

 maybe

1.23

 perhaps

1.17

maybe

0.98

perhaps

0.96

 Maybe

0.88

 possibly

0.87

 misschien

0.85

 Perhaps

0.84

 vielleicht

0.82

 talvez

0.82

Activations Density 0.120%

phrases indicating exceptions or exclusions

No Comments

No Known Activations