INDEX

Explanations

references to teaching and education

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Welles

-0.69

Malley

-0.65

 Barrow

-0.63

onesi

-0.63

 Stanley

-0.62

Phal

-0.61

瘩

-0.60

 Maloney

-0.59

IBarButtonItem

-0.59

Bhd

-0.59

POSITIVE LOGITS

 teach

1.52

 teaches

1.47

 teachers

1.41

 teaching

1.37

teach

1.36

Teach

1.34

teaching

1.34

 taught

1.32

 Teach

1.31

 TEACH

1.30

Activations Density 0.050%

references to teaching and education

No Comments

No Known Activations