INDEX

Explanations

terms related to patterns and patient data in medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 MonoBehaviour

-0.74

twimg

-0.74

BeginContext

-0.69

ITHUB

-0.66

SpringRunner

-0.64

تقاوى

-0.61

maxcdn

-0.61

клопе

-0.60

 Foxx

-0.60

velser

-0.60

POSITIVE LOGITS

PAT

0.98

 patterns

0.93

PAT

0.90

 Patterns

0.90

Patterns

0.87

pat

0.82

 pattern

0.79

patterns

0.76

Patterson

0.76

Pat

0.73

Activations Density 0.283%

terms related to patterns and patient data in medical contexts

No Comments

No Known Activations