INDEX

Explanations

words indicating something is a component of a larger thing and the larger thing has boundaries.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.09

-0.49

-0.48

-0.47

new

-0.46

-0.45

-0.44

-0.43

POSITIVE LOGITS

 myſelf

1.11

 itſelf

1.10

ViewFeatures

1.08

 Monfieur

1.03

 pleaſure

1.02

 Theſe

1.01

 kasarigan

0.98

Efq

0.97

 whoſe

0.96

 greateſt

0.96

Activations Density 2.753%

words indicating something is a component of a larger thing and the larger thing has boundaries.

No Comments

No Known Activations