INDEX

Explanations

concepts related to healthcare and its implementation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.76

or

-0.69

and

-0.69

to

-0.61

ten

-0.60

den

-0.59

one

-0.58

has

-0.58

POSITIVE LOGITS

ſelf

1.56

ſelves

1.55

 Jefus

1.52

 myſelf

1.49

 Majefty

1.48

 itſelf

1.48

 Monfieur

1.46

Efq

1.41

 Shakspeare

1.40

 Reſ

1.39

Activations Density 0.683%

concepts related to healthcare and its implementation

No Comments

No Known Activations