INDEX

Explanations

the phrase "[something] in the form of [something]" and concepts that are analogous to that phrase.

oai_token-act-pair · gemini-2.0-flash

form

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

بله

-0.55

RunAsync

-0.54

fromnode

-0.54

ophagus

-0.53

 order

-0.51

 насељу

-0.51

RegressionTest

-0.51

EnableWeb

-0.50

RenderAtEndOf

-0.49

Kariera

-0.49

POSITIVE LOGITS

RuleContext

0.58

Dono

0.53

 Shakspeare

0.51

 Merr

0.50

 everlasting

0.50

Efq

0.49

="@+

0.49

 Crot

0.49

 meurt

0.48

 Dott

0.48

Activations Density 1.763%

the phrase "[something] in the form of [something]" and concepts that are analogous to that phrase.

form

No Comments

No Known Activations