INDEX

Explanations

survey findings or research results

oai_token-act-pair · gpt-3.5-turbo

survey results or findings from studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

von

-0.83

inventoryQuantity

-0.81

arantine

-0.73

displayText

-0.69

assetsadobe

-0.69

awar

-0.68

cious

-0.67

ascus

-0.65

ico

-0.65

endars

-0.64

POSITIVE LOGITS

 that

1.11

 widespread

0.90

that

0.87

 significant

0.83

 similarities

0.76

 disparities

0.76

 majorities

0.74

 negligible

0.74

 overwhelmingly

0.73

Activations Density 0.140%

survey findings or research results

survey results or findings from studies

No Comments

No Known Activations