INDEX

Explanations

verbs often associated with actions taken by people, especially in positions of power.

oai_token-act-pair · gemini-2.0-flash

news articles

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

SequentialGroup

-0.67

PhysRevD

-0.65

Plus

-0.61

 Resonance

-0.59

 secondly

-0.59

 Plus

-0.57

andinavia

-0.57

 cioc

-0.57

AddTagHelper

-0.56

pleen

-0.55

POSITIVE LOGITS

setDo

0.47

ba

0.44

aarrggbb

0.43

 NSCoder

0.42

aufen

0.40

protos

0.40

urm

0.38

SpringBootTest

0.36

 iprot

0.36

ásban

0.36

Activations Density 19.222%

verbs often associated with actions taken by people, especially in positions of power.

news articles

No Comments

No Known Activations