INDEX

Explanations

references to Toll-like receptors (TLRs) and their associated patterns or receptors in immunological contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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

♥️

-0.64

 Weeknd

-0.63

 Commencez

-0.62

 geschlagen

-0.61

kämp

-0.61

ABI

-0.60

🥲

-0.60

Tir

-0.59

Kf

-0.59

enschappen

-0.59

POSITIVE LOGITS

TLR

1.70

TLR

1.30

">:

0.68

ėms

0.66

')],

0.65

 Decken

0.63

 Iman

0.60

klere

0.60

 Römer

0.59

 router

0.59

Activations Density 0.002%

references to Toll-like receptors (TLRs) and their associated patterns or receptors in immunological contexts

No Comments

No Known Activations