INDEX

Explanations

references to medical conditions and therapies

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

protoimpl

-0.68

 HasFactory

-0.68

 pinulongan

-0.66

ển

-0.64

تقاوى

-0.64

 Autorizaciones

-0.62

ſelf

-0.62

iffion

-0.61

 كومونز

-0.61

MessageTagHelper

-0.61

POSITIVE LOGITS

void

0.60

 void

0.55

Rüyada

0.50

 setTimeout

0.50

otone

0.47

 abuso

0.47

 null

0.47

clearTimeout

0.46

 annuelle

0.45

null

0.43

Activations Density 0.038%

references to medical conditions and therapies

No Comments

No Known Activations