INDEX

Explanations

indicators of medical research or clinical study context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

DoubleQuotes

-0.61

ագրություններ

-0.60

']>;

-0.56

വല

-0.56

 jugé

-0.54

 condamné

-0.53

ษัท

-0.52

 hâte

-0.51

casque

-0.50

 newOwner

-0.49

POSITIVE LOGITS

AsUp

0.73

 kasarigan

0.71

protoimpl

0.65

 című

0.59

PreferredItem

0.57

UserScript

0.56

prefixer

0.56

hdys

0.56

WebVitals

0.54

 PeEnEo

0.53

Activations Density 0.560%

indicators of medical research or clinical study context

No Comments

No Known Activations