INDEX

Explanations

the word "of" preceded by a word indicating quantity

oai_token-act-pair · gemini-2.0-flash

occurrences of "many of"

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

of

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

it

-1.19

it

-0.78

It

-0.71

It

-0.68

 оно

-0.66

它

-0.55

มัน

-0.52

 AssemblyVersion

-0.52

nó

-0.49

 нём

-0.48

POSITIVE LOGITS

 them

0.96

ScopeManager

0.79

 then

0.74

RenderAtEndOf

0.73

 ujednoznacz

0.72

原始内容存档于

0.71

DoubleQuotes

0.69

transQ

0.68

/*

0.68

 THEM

0.67

Activations Density 0.846%

the word "of" preceded by a word indicating quantity

occurrences of "many of"

of

No Comments

No Known Activations