INDEX

Explanations

negative reviews or criticisms about experiences or products

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

 للمعارف

-0.67

makeConstraints

-0.66

 getItemCount

-0.57

ImmutableList

-0.54

ziplin

-0.53

+#+#

-0.53

 mẽ

-0.51

Παραπομπές

-0.49

ḵ

-0.47

cinated

-0.47

POSITIVE LOGITS

 worse

0.77

Worse

0.77

 Worse

0.76

 ogóle

0.74

 disappointing

0.71

 peggio

0.71

 worst

0.68

 poor

0.65

 unattractive

0.65

 unfavourable

0.64

Activations Density 0.197%

negative reviews or criticisms about experiences or products

No Comments

No Known Activations

negative reviews or criticisms about experiences or products

No Comments

No Known Activations