INDEX

Explanations

technical or instruction manual language related to processes.

oai_token-act-pair · gemini-2.0-flash

technical tags and identifiers

np_token-act-pair-logits · gpt-4o-mini

Events and Processes

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 OrderedDict

-0.50

 siglos

-0.47

 manhã

-0.45

清晨

-0.45

 late

-0.45

第二天

-0.44

 yesterday

-0.44

 Tuesday

-0.43

oke

-0.43

翌日

-0.43

POSITIVE LOGITS

 CreateTagHelper

0.88

 Infórmanos

0.83

tagHelperRunner

0.83

Datuak

0.81

出版年

0.81

 CascadeType

0.77

CloseOperation

0.73

RegressionTest

0.68

 loob

0.68

ArgumentParser

0.67

Activations Density 1.010%

technical or instruction manual language related to processes.

technical tags and identifiers

Events and Processes

No Comments

No Known Activations