INDEX

Explanations

words related to pain and depression

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Rhestr

-0.68

 propOrder

-0.65

 impea

-0.64

intios

-0.59

arella

-0.58

rungsseite

-0.57

IUrlHelper

-0.57

Ĝ

-0.54

 impeach

-0.54

Nationalité

-0.50

POSITIVE LOGITS

 pain

2.38

 Pain

2.17

Pain

2.16

pain

2.02

 PAIN

1.93

 pains

1.62

 douleur

1.62

 painful

1.57

 Schmerz

1.55

 dolor

1.53

Activations Density 0.996%

words related to pain and depression

No Comments

No Known Activations