INDEX

Explanations

instances of the word "auto" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jspx

-0.97

URLException

-0.89

adpleegd

-0.88

 grecque

-0.87

 StringField

-0.86

 Мексичка

-0.85

 useAppContext

-0.84

 Anfitrión

-0.81

Kraken

-0.81

 méri

-0.80

POSITIVE LOGITS

 Auto

2.96

 auto

2.93

Auto

2.77

 AUTO

2.71

auto

2.69

AUTO

2.36

 autos

1.90

 Autos

1.79

autos

1.75

setAuto

1.73

Activations Density 0.030%

instances of the word "auto" and its variations

No Comments

No Known Activations