INDEX

Explanations

mentions of research and studies, particularly in medical or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Research

-0.81

Research

-0.78

 research

-0.76

 RESEARCH

-0.73

research

-0.70

NameInMap

-0.58

RESEARCH

-0.57

 researched

-0.55

+#+

-0.54

 researcher

-0.54

POSITIVE LOGITS

 into

0.64

Gate

0.63

 findings

0.58

 createState

0.57

 conducted

0.57

gate

0.57

员

0.55

 agendas

0.55

 institutes

0.54

Vidite

0.53

Activations Density 0.156%

mentions of research and studies, particularly in medical or scientific contexts

No Comments

No Known Activations