INDEX

Explanations

date and time references, specifically those related to weeks and years

oai_token-act-pair · gemini-2.0-flash

Time Periods

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.68

<bos>

-0.61

’

-0.57

-0.44

-0.41

-0.39

どの

-0.39

-0.38

-0.37

POSITIVE LOGITS

GEBURTSDATUM

1.12

 intptr

1.04

 للاسماء

0.98

RegressionTest

0.94

 оригіналу

0.91

 Audiodateien

0.88

MockMvc

0.87

 يتيمه

0.85

+:+

0.85

NameInMap

0.84

Activations Density 0.113%

date and time references, specifically those related to weeks and years

Time Periods

No Comments

No Known Activations