INDEX

Explanations

terms associated with healthcare and intervention strategies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ſelf

-1.06

 InputDecoration

-0.92

ſelves

-0.92

^(@)

-0.84

 Houſe

-0.83

Efq

-0.83

BibitemShut

-0.83

 Monfieur

-0.82

 Majefty

-0.81

neſs

-0.78

POSITIVE LOGITS

ho

0.54

nu

0.50

hy

0.47

vol

0.46

vo

0.46

 sure

0.45

tab

0.45

фера

0.44

link

0.44

ny

0.42

Activations Density 1.528%

terms associated with healthcare and intervention strategies

No Comments

No Known Activations