INDEX

Explanations

elements related to conflict and character motivations in a narrative

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

extAlignment

-0.51

 resourceCulture

-0.41

 IconData

-0.39

 rhestr

-0.36

 purpoſe

-0.34

 hayas

-0.33

 dAtA

-0.33

 woorden

-0.33

Аб

-0.33

новниш

-0.33

POSITIVE LOGITS

 weekly

0.80

 periodically

0.67

 occasionally

0.66

 monthly

0.66

毎回

0.64

每周

0.64

 regularly

0.64

 frequently

0.64

 occasional

0.64

weekly

0.62

Activations Density 0.134%

elements related to conflict and character motivations in a narrative

No Comments

No Known Activations