INDEX

Explanations

references to auras, particularly in association with the name "Chandra" and "Chapman."

oai_token-act-pair · gpt-3.5-turbo

references to auras and their associated meanings

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

indust

-0.81

ensible

-0.81

riter

-0.79

ional

-0.79

ensibly

-0.75

erences

-0.75

ding

-0.74

actively

-0.74

sett

-0.73

coon

-0.71

POSITIVE LOGITS

uras

0.79

 eclipse

0.78

 misunder

0.74

 tornado

0.70

 restraining

0.69

aur

0.68

 Jinn

0.68

 Spectre

0.66

 coron

0.66

è¦ļéĨĴ

0.65

Activations Density 0.028%

references to auras, particularly in association with the name "Chandra" and "Chapman."

references to auras and their associated meanings

No Comments

No Known Activations