INDEX

Explanations

pronouns in various contexts

oai_token-act-pair · gemini-2.0-flash

some

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 some

-0.61

 their

-0.56

-0.52

-0.51

-0.49

all

-0.49

 your

-0.48

all

-0.47

Some

-0.47

-0.46

POSITIVE LOGITS

LookAnd

1.23

^(@)

1.13

Efq

1.13

tagHelperRunner

1.11

 myſelf

1.09

\{\\

1.07

SequentialGroup

1.07

 leſs

1.05

StoryboardSegue

1.05

ConstraintMaker

1.04

Activations Density 7.589%

pronouns in various contexts

some

No Comments

No Known Activations