INDEX

Explanations

references to medications and treatment-related terms

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

InitVars

-0.91

 ujednoznacz

-0.90

 disambiguazione

-0.90

EDEFAULT

-0.90

parsedMessage

-0.85

SharedDtor

-0.85

IUrlHelper

-0.84

AddHtmlAttribute

-0.82

 autorytatywna

-0.81

 Мексичка

-0.81

POSITIVE LOGITS

vil

0.47

ge

0.46

0.45

ra

0.44

ro

0.44

↵↵↵

0.43

setIcon

0.43

↵

0.43

 note

0.43

Activations Density 0.005%

references to medications and treatment-related terms

No Comments

No Known Activations