INDEX

Explanations

terms related to healthcare performance and evaluation

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

 surla

-0.71

 katanya

-0.58

stdc

-0.57

 silahkan

-0.53

 aantal

-0.51

mybatisplus

-0.51

 demás

-0.51

 demais

-0.50

 restantes

-0.49

pushFollow

-0.48

POSITIVE LOGITS

0.96

 only

0.95

 plenty

0.90

no

0.88

 little

0.86

 considerable

0.86

 something

0.85

 neither

0.83

 both

0.83

an

0.82

Activations Density 1.153%

terms related to healthcare performance and evaluation

No Comments

No Known Activations