INDEX

Explanations

various usages of the word "put"

oai_token-act-pair · gemini-2.0-flash

instances of "put"

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

put/putting

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 الحره

-0.75

tvguidetime

-0.52

 lèvres

-0.47

 remercier

-0.47

 accepté

-0.46

 giustizia

-0.46

^\

-0.43

 représentants

-0.42

 attendre

-0.42

oracle

-0.41

POSITIVE LOGITS

 aside

0.71

 together

0.69

principalTable

0.67

Архівовано

0.66

ParallelGroup

0.64

 nonUne

0.63

BarItem

0.62

 getItemId

0.62

uelo

0.60

JspWriter

0.60

Activations Density 1.880%

various usages of the word "put"

instances of "put"

put/putting

No Comments

No Known Activations