INDEX

Explanations

words related to dogs, especially their behavior and training, including lunging and herding

oai_token-act-pair · gemini-2.0-flash

dogs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

AndEndTag

-0.74

uxxxx

-0.60

IVEREF

-0.60

 resourceCulture

-0.58

SequentialGroup

-0.56

 noDo

-0.51

InjectAttribute

-0.51

SharedCtor

-0.51

WebControls

-0.49

Denn

-0.48

POSITIVE LOGITS

posób

0.57

segno

0.57

ebenarnya

0.55

lorette

0.55

 distracting

0.55

 historiques

0.53

 exercised

0.52

 professionali

0.51

appliquer

0.50

 Entfernung

0.50

Activations Density 0.572%

words related to dogs, especially their behavior and training, including lunging and herding

dogs

No Comments

No Known Activations