INDEX

Explanations

terms related to disease, hosts, and biological interactions

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Romains

-0.53

 peuples

-0.51

])));

-0.50

 PARSER

-0.50

 sagesse

-0.49

 '+':

-0.49

󠁿

-0.49

 recently

-0.48

 Exteriores

-0.48

)]=

-0.47

POSITIVE LOGITS

tvguidetime

0.77

contentLoaded

0.73

 cref

0.69

NUMX

0.65

 AssemblyTitle

0.64

⤹

0.58

rawDesc

0.52

msford

0.51

ignite

0.51

 <=",

0.51

Activations Density 0.133%

terms related to disease, hosts, and biological interactions

No Comments

No Known Activations