INDEX

Explanations

terms related to medical research and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Such

-0.60

BeginInit

-0.59

 Such

-0.58

ContentAsync

-0.55

poň

-0.53

 solcher

-0.52

 slik

-0.52

drage

-0.52

 côtés

-0.52

 pudieran

-0.51

POSITIVE LOGITS

 that

1.04

 originating

0.90

 whose

0.88

 originally

0.86

 created

0.85

 located

0.83

 founded

0.81

 born

0.79

 belonging

0.77

 whoſe

0.76

Activations Density 0.565%

terms related to medical research and organizations

No Comments

No Known Activations