INDEX

Explanations

mentions of characters and stories in books

oai_token-act-pair · gemini-2.0-flash

verbs related to arrival and discovery

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

Movement verbs

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

ValueStyle

-1.02

AccessorTable

-0.75

Geplaatst

-0.69

 pouvoit

-0.65

 étoit

-0.64

IntoConstraints

-0.64

adaptiveStyles

-0.64

 vectorielle

-0.63

Jeografia

-0.63

 Walkover

-0.62

POSITIVE LOGITS

 arrive

0.65

üf

0.60

fly

0.60

 arrives

0.59

drift

0.58

 discover

0.57

 drift

0.56

""",

0.55

]")

0.54

discover

0.53

Activations Density 2.536%

mentions of characters and stories in books

verbs related to arrival and discovery

Movement verbs

No Comments

No Known Activations