INDEX

Explanations

words related to investigations and inquiries

oai_token-act-pair · gemini-2.0-flash

terms related to investigations

np_token-act-pair-logits · gpt-4o-mini

investigation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

تقاوى

-0.98

 beginnetje

-0.90

 المعيارى

-0.85

 Monfieur

-0.78

存于互联网档案馆

-0.77

Efq

-0.77

 ſtand

-0.76

 дописавши

-0.74

 ſtate

-0.73

 myſelf

-0.73

POSITIVE LOGITS

 plan

0.60

SequentialGroup

0.58

 ус

0.49

platz

0.47

run

0.46

 method

0.46

Act

0.44

0.43

Get

0.43

’

0.43

Activations Density 6.899%

words related to investigations and inquiries

terms related to investigations

investigation

No Comments

No Known Activations