INDEX

Explanations

words appearing in formal writing that are related to research, disagreement, and the legal system.

oai_token-act-pair · gemini-2.0-flash

Words ending in "ory"/"ary"

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 counter

-0.97

counter

-0.85

Противо

-0.82

 contrasting

-0.81

 oppos

-0.81

 opposing

-0.81

 opposite

-0.81

 Counter

-0.80

 AssemblyCulture

-0.78

Personensuche

-0.78

POSITIVE LOGITS

 portion

0.47

 componente

0.47

typeDefinition

0.45

 defaultValue

0.42

 STEWART

0.40

 belas

0.40

Std

0.40

梁

0.40

 вер

0.39

eseen

0.39

Activations Density 52.478%

words appearing in formal writing that are related to research, disagreement, and the legal system.

Words ending in "ory"/"ary"

No Comments

No Known Activations