INDEX

Explanations

the word "meta" or variations of it in the text

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "meta" or self-referential analysis

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Interstitial

-0.85

iens

-0.77

çİĭ

-0.69

IBLE

-0.69

HCR

-0.65

shire

-0.65

 Parables

-0.65

teenth

-0.64

ESCO

-0.64

 Shooter

-0.63

POSITIVE LOGITS

ethical

0.95

alyses

0.89

plot

0.87

 guiActiveUn

0.80

allo

0.79

 meta

0.78

ethyl

0.75

meta

0.74

hei

0.74

econom

0.73

Activations Density 0.006%

the word "meta" or variations of it in the text

references to the concept of "meta" or self-referential analysis

No Comments

No Known Activations