INDEX

Explanations

references to medical themes and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

:✨

-0.90

 kaynağından

-0.89

parsedMessage

-0.87

躇

-0.86

 defaultstate

-0.85

 AssemblyCulture

-0.84

TestingModule

-0.83

TypedDataSet

-0.82

 <=",

-0.81

IBOutlet

-0.80

POSITIVE LOGITS

 medical

1.96

 Medical

1.89

Medical

1.76

medical

1.65

 MEDICAL

1.62

MEDICAL

1.58

 medica

1.23

 medically

1.21

 médical

1.08

 biomedical

1.06

Activations Density 0.045%

references to medical themes and terminology

No Comments

No Known Activations