INDEX

Explanations

quantitative data or measurements

oai_token-act-pair · gpt-3.5-turbo

phrases related to quantification and analysis

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

HOME

-0.80

 Mansion

-0.72

lihood

-0.69

 blades

-0.67

 spare

-0.64

 Sutherland

-0.63

 purse

-0.60

 Papua

-0.59

 pity

-0.58

 Slayer

-0.58

POSITIVE LOGITS

itatively

1.64

itative

1.18

ifiable

1.17

ifiers

1.05

idian

1.04

ifier

1.03

ifying

1.02

imet

1.01

ified

1.01

 quant

0.99

Activations Density 0.025%

quantitative data or measurements

phrases related to quantification and analysis

No Comments

No Known Activations