INDEX

Explanations

legal terms related to liability and claims

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

 Picchu

-0.50

mlb

-0.47

كذا

-0.47

IEFS

-0.45

owulf

-0.45

ILayout

-0.45

ėjimo

-0.44

iastes

-0.43

 consider

-0.43

 indeb

-0.43

POSITIVE LOGITS

 ARISING

3.61

 arising

1.39

 arises

1.05

 arise

1.04

arise

0.98

 arisen

0.95

 arose

0.86

0.82

 getItemId

0.79

//

0.76

Activations Density 0.000%

legal terms related to liability and claims

No Comments

No Known Activations