INDEX

Explanations

terms related to medical conditions or treatments and their outcomes

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

Jeografia

-0.73

 What

-0.54

Did

-0.51

 Which

-0.49

 Such

-0.49

You

-0.48

 Может

-0.48

 Increased

-0.47

 Whether

-0.47

Why

-0.46

POSITIVE LOGITS

 Club

0.88

 Unit

0.87

 Panel

0.85

 Agency

0.82

 Module

0.82

 Station

0.81

 Platform

0.81

 Group

0.81

 Suite

0.80

 Scheme

0.79

Activations Density 2.499%

terms related to medical conditions or treatments and their outcomes

No Comments

No Known Activations