INDEX

Explanations

references to brain health and related medical procedures.

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

phrases related to medical conditions or procedures involving the brain.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

words and phrases related to the brain and brain-related medical conditions or procedures.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

참고

-0.63

 overras

-0.61

 EconPapers

-0.53

ρά

-0.51

ienia

-0.50

...')

-0.50

 Sense

-0.49

sys

-0.49

lorette

-0.49

jelder

-0.48

POSITIVE LOGITS

waves

0.83

 TestBed

0.79

 للمعارف

0.76

 Brain

0.74

 brains

0.73

 BRAIN

0.72

endregion

0.69

 createState

0.68

 Brains

0.67

 brain

0.66

Activations Density 0.107%

references to brain health and related medical procedures.

phrases related to medical conditions or procedures involving the brain.

words and phrases related to the brain and brain-related medical conditions or procedures.

No Comments

No Known Activations