INDEX

Explanations

words related to medical or health contexts, specifically indicating conditions or treatments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 waard

-0.49

lossenen

-0.47

 apellido

-0.47

playable

-0.46

griffen

-0.45

 dila

-0.45

 Konink

-0.44

entes

-0.44

venes

-0.44

venge

-0.43

POSITIVE LOGITS

ie

2.69

IE

2.25

ies

1.96

IES

1.60

ie

1.58

IE

1.39

Ie

1.29

ieg

1.27

iee

1.20

Ie

1.13

Activations Density 1.992%

words related to medical or health contexts, specifically indicating conditions or treatments

No Comments

No Known Activations