INDEX

Explanations

comparative statements, particularly those indicating a lesser degree or status

oai_token-act-pair · gpt-3.5-turbo

words and phrases indicating degrees of comparison or evaluations of people and groups

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

osate

-0.77

 VIDEOS

-0.76

 Solitaire

-0.71

 Attribution

-0.69

 roundup

-0.69

 simulations

-0.68

 giveaway

-0.67

 sequence

-0.66

ģ«

-0.66

 closures

-0.66

POSITIVE LOGITS

educated

1.45

 talented

1.35

haired

1.27

 educated

1.25

 unemployed

1.23

skilled

1.23

 bearded

1.20

trained

1.19

 wealthy

1.19

 skilled

1.18

Activations Density 0.240%

comparative statements, particularly those indicating a lesser degree or status

words and phrases indicating degrees of comparison or evaluations of people and groups

No Comments

No Known Activations