INDEX

Explanations

numerical figures and percentages

oai_token-act-pair · gpt-3.5-turbo

ID codes or numerical identifiers associated with various entities or data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 ambassadors

-0.70

thumbnails

-0.69

athered

-0.69

 facilit

-0.68

bip

-0.67

²¾

-0.66

 facilitated

-0.64

 VIDE

-0.63

 bonded

-0.61

conservancy

-0.61

POSITIVE LOGITS

OTAL

0.73

daq

0.71

nington

0.68

oice

0.67

throw

0.66

Answer

0.66

 Almighty

0.64

 ERROR

0.64

racuse

0.63

oran

0.63

Activations Density 0.211%

numerical figures and percentages

ID codes or numerical identifiers associated with various entities or data points

No Comments

No Known Activations

numerical figures and percentages

ID codes or numerical identifiers associated with various entities or data points

No Comments

No Known Activations