INDEX

Explanations

places or locations

oai_token-act-pair · gpt-3.5-turbo

locations and settings mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

athered

-0.67

stood

-0.66

FontSize

-0.64

 spans

-0.59

anse

-0.58

 distinguishes

-0.56

Parameter

-0.55

 indications

-0.55

xtap

-0.55

 nods

-0.55

POSITIVE LOGITS

 voluntarily

1.03

 willingly

1.00

 unprepared

0.98

 undet

0.97

 unaccompanied

0.95

 alone

0.93

 expecting

0.93

 smelling

0.91

 unnoticed

0.88

 unsc

0.87

Activations Density 0.341%

places or locations

locations and settings mentioned in the text

No Comments

No Known Activations