INDEX

Explanations

personal pronouns, especially "myself," "me," "my," "ourselves" and "them"

oai_token-act-pair · gemini-2.0-flash

myself

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.91

-0.80

↵↵

-0.73

an

-0.70

all

-0.68

in

-0.67

-0.60

the

-0.59

-0.57

POSITIVE LOGITS

 itſelf

1.54

Efq

1.45

 myſelf

1.41

 Majefty

1.37

ſelves

1.37

 Jefus

1.37

 Reſ

1.36

 themſelves

1.36

ſelf

1.34

 ſeveral

1.34

Activations Density 4.363%

personal pronouns, especially "myself," "me," "my," "ourselves" and "them"

myself

No Comments

No Known Activations