INDEX

Explanations

the word "one" being used to emphasize a singular entity or item

oai_token-act-pair · gemini-2.0-flash

one

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

tvguidetime

-1.05

 CURIAM

-0.99

 Walkover

-0.93

aarrggbb

-0.86

脚注の使い方

-0.85

ScopeManager

-0.85

 "..\..\..\

-0.85

 ModelExpression

-0.83

FunctionFlags

-0.83

MLLoader

-0.83

POSITIVE LOGITS

 houſe

0.79

$_"

0.69

 purpoſe

0.64

 pleaſure

0.64

 poffe

0.63

 ſen

0.61

 ſame

0.61

 gagné

0.60

 fhew

0.60

 pulito

0.60

Activations Density 0.233%

the word "one" being used to emphasize a singular entity or item

one

No Comments

No Known Activations