INDEX

Explanations

phrases or terms that are commonly known as something else

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce or identify entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

midt

-0.81

ega

-0.79

ORTS

-0.73

essim

-0.72

onen

-0.70

atche

-0.70

olate

-0.68

inth

-0.67

erial

-0.66

YR

-0.65

POSITIVE LOGITS

pires

1.01

pired

0.85

phy

0.76

pire

0.75

calling

0.74

criptions

0.73

 well

0.73

[|

0.71

 regards

0.70

piring

0.66

Activations Density 0.090%

phrases or terms that are commonly known as something else

phrases that introduce or identify entities or concepts

No Comments

No Known Activations