INDEX

Explanations

time-related words and phrases that imply a cause-and-effect relationship.

oai_token-act-pair · gemini-2.0-flash

subsequent events

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

 nakalista

-0.64

KommentareTeilen

-0.57

 LIMIT

-0.55

abestanden

-0.54

 Gleaner

-0.51

astify

-0.50

/*

-0.49

ValueStyle

-0.47

UVWXYZ

-0.47

 Wiktionnaire

-0.46

POSITIVE LOGITS

]--;

0.57

eriks

0.53

MemoryWarning

0.53

Mej

0.52

StructEnd

0.51

 Topics

0.51

 ModelExpression

0.50

исленность

0.49

ValueGenerated

0.49

CloseOperation

0.49

Activations Density 3.028%

time-related words and phrases that imply a cause-and-effect relationship.

subsequent events

No Comments

No Known Activations