INDEX

Explanations

tokens in argumentative writing

oai_token-act-pair · gemini-2.0-flash

possessive pronouns

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Ours

-1.05

herself

-0.97

 Оно

-0.97

Our

-0.96

Our

-0.92

himself

-0.89

themselves

-0.88

OUR

-0.88

 Itself

-0.88

 ours

-0.87

POSITIVE LOGITS

 свою

0.57

seu

0.56

 své

0.54

 your

0.52

my

0.50

her

0.49

 seus

0.49

 свой

0.49

 swoje

0.49

 своё

0.46

Activations Density 4.054%

tokens in argumentative writing

possessive pronouns

No Comments

No Known Activations