INDEX

Explanations

references to inadequacies or failures in medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 tslint

-0.53

,‎

-0.51

 ayrıca

-0.50

 Schot

-0.49

AndEndTag

-0.49

middels

-0.49

 parallelogram

-0.49

fony

-0.48

 fija

-0.48

OMI

-0.48

POSITIVE LOGITS

too

1.18

Too

1.07

too

1.07

 insufficient

1.05

Too

1.04

TOO

0.97

 zbyt

0.89

 слишком

0.88

 lack

0.87

TOO

0.84

Activations Density 0.497%

references to inadequacies or failures in medical contexts

No Comments

No Known Activations