INDEX

Explanations

phrases related to the Deepwater Horizon incident

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

cules

-0.81

ICAN

-0.79

icans

-0.71

orious

-0.70

oppable

-0.69

uably

-0.69

Ĥİ

-0.69

 Speedway

-0.68

icable

-0.68

icip

-0.65

POSITIVE LOGITS

water

0.96

 vein

0.89

ened

0.88

est

0.83

ly

0.82

lings

0.80

ness

0.80

anian

0.75

deep

0.75

ening

0.74

Activations Density 0.014%

phrases related to the Deepwater Horizon incident

No Comments

No Known Activations