INDEX

Explanations

terms related to medical diagnostics and conditions

oai_token-act-pair · gpt-4o-mini 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

 diseased

-0.60

 snee

-0.60

GraphicsUnit

-0.58

disease

-0.58

lamydia

-0.57

:+:

-0.57

Tumor

-0.56

 tumor

-0.54

 disease

-0.53

GenerationType

-0.51

POSITIVE LOGITS

 تانيه

0.60

ilistic

0.55

UserScript

0.55

DRESS

0.54

 DRESS

0.54

 متعلقه

0.53

sterious

0.52

 Extragalactic

0.52

Fatal

0.51

Autoritní

0.51

Activations Density 1.357%

terms related to medical diagnostics and conditions

No Comments

No Known Activations