INDEX

Explanations

phrases related to personal experiences and choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Biôgrafia

-0.57

енча

-0.52

ταν

-0.51

 prece

-0.51

 <<<<<<<<<<<<<<

-0.48

Abr

-0.48

 obliga

-0.48

 Involved

-0.47

issi

-0.47

postalCode

-0.47

POSITIVE LOGITS

 suits

1.79

 suit

1.71

fit

1.71

 fits

1.70

 suited

1.61

fits

1.45

fit

1.41

suited

1.37

suit

1.37

suits

1.34

Activations Density 0.232%

phrases related to personal experiences and choices

No Comments

No Known Activations