INDEX

Explanations

instances of the word "and" along with surrounding words

oai_token-act-pair · gemini-2.0-flash

words with unique characters or variations

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

and

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

enumi

-1.00

enumii

-0.90

UserScript

-0.86

+#+#

-0.77

 nakalista

-0.74

NameInMap

-0.74

/\.

-0.74

 Italijanski

-0.72

<bos>

-0.71

bootstrapcdn

-0.70

POSITIVE LOGITS

 مواليد

0.59

 tartalomajánló

0.58

 myſelf

0.57

 becauſe

0.57

 againſt

0.57

 Theſe

0.55

 itſelf

0.54

 Româ

0.54

 whoſe

0.53

 poffible

0.53

Activations Density 1.891%

instances of the word "and" along with surrounding words

words with unique characters or variations

and

No Comments

No Known Activations