INDEX

Explanations

words related to medical assessments and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

matchCondition

-0.70

mergeFrom

-0.70

 Roskov

-0.66

:✨

-0.64

XmlEnum

-0.63

webElementGuid

-0.62

onAttach

-0.60

fromUtf

-0.59

CONSIN

-0.57

 calendriers

-0.56

POSITIVE LOGITS

Needed

0.67

 needed

0.67

needed

0.64

mtrl

0.62

 Needed

0.61

 necessary

0.60

 unnecessary

0.60

necessary

0.57

必要がある

0.55

 Required

0.55

Activations Density 0.771%

words related to medical assessments and treatments

No Comments

No Known Activations