INDEX

Explanations

instances of calling or naming something, particularly in relation to labels or terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

quiao

-0.63

psack

-0.61

 Wallflower

-0.58

 rade

-0.58

pios

-0.56

 Meiji

-0.56

 }}"></

-0.56

 Wheaton

-0.55

örté

-0.55

 Eventually

-0.55

POSITIVE LOGITS

Called

1.07

 CALLED

1.01

 called

1.01

 Called

0.99

called

0.97

 termed

0.90

 coined

0.84

 llamó

0.83

 chiamato

0.83

 kalla

0.81

Activations Density 0.147%

instances of calling or naming something, particularly in relation to labels or terms

No Comments

No Known Activations