INDEX

Explanations

terms related to scientific authority and leadership in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Ge

-0.74

uku

-0.65

Ge

-0.65

 AdapterView

-0.64

Ku

-0.63

land

-0.63

 Mart

-0.63

 Land

-0.62

la

-0.62

POSITIVE LOGITS

 himſelf

1.13

ſelf

1.06

 poffe

1.06

 myſelf

1.03

 themſelves

0.99

 neceffary

0.99

 itſelf

0.98

 poffible

0.96

 Quir

0.95

 havaianas

0.94

Activations Density 0.111%

terms related to scientific authority and leadership in research contexts

No Comments

No Known Activations