INDEX

Explanations

references to medical conditions and concepts related to health

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 getPassword

-0.57

uarts

-0.55

 ivelany

-0.52

 setShow

-0.52

pædia

-0.52

ellees

-0.51

 setLoading

-0.51

thèse

-0.50

]--;

-0.50

POSITIVE LOGITS

protoimpl

0.66

 noires

0.66

RunAsync

0.65

 själva

0.62

 propOrder

0.60

 scolaires

0.58

 habet

0.58

 positifs

0.58

 estekak

0.57

 religieuses

0.56

Activations Density 0.630%

references to medical conditions and concepts related to health

No Comments

No Known Activations