INDEX

Explanations

the word "a" or "the" in conjunction with other descriptive words

oai_token-act-pair · gemini-2.0-flash

words starting with 'a'

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

article "a" or "an"

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

AutoScaleMode

-0.54

 prossimo

-0.54

visející

-0.54

 appelés

-0.52

 bestaande

-0.51

 compréhension

-0.50

tagHelperRunner

-0.49

seamnă

-0.49

ientôt

-0.49

 courbe

-0.49

POSITIVE LOGITS

addContainerGap

0.66

esez

0.63

complexType

0.62

 Ause

0.62

ंदीखरीदारी

0.62

 tactic

0.61

 idea

0.59

 Мексичка

0.58

ніципа

0.58

 development

0.54

Activations Density 1.498%

the word "a" or "the" in conjunction with other descriptive words

words starting with 'a'

article "a" or "an"

No Comments

No Known Activations