INDEX

Explanations

phrases related to specific medical conditions or procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 Startseite

-0.50

googleapis

-0.49

ngdoc

-0.46

ėtų

-0.45

 Kauf

-0.44

 state

-0.44

MLLoader

-0.43

 State

-0.43

tagli

-0.43

Narrator

-0.43

POSITIVE LOGITS

 hotel

1.08

hotel

0.94

 minibar

0.93

Hotel

0.86

 toiletries

0.82

 Hotel

0.79

 hotels

0.79

 hote

0.78

 hotell

0.78

HOTEL

0.77

Activations Density 0.180%

phrases related to specific medical conditions or procedures

No Comments

No Known Activations