INDEX

Explanations

words related to homogeneity and uniformity

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "homo" related to various contexts of society and biology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

CLASSIFIED

-0.73

 drip

-0.69

UGE

-0.69

DER

-0.67

REE

-0.66

 Blossom

-0.65

 canopy

-0.65

Charge

-0.63

UGH

-0.62

MK

-0.61

POSITIVE LOGITS

estead

1.32

ogeneous

1.27

ogenous

1.27

ogeneity

1.26

onym

1.25

onymous

1.21

icidal

1.17

ogen

1.15

oph

1.09

ogene

1.09

Activations Density 0.020%

words related to homogeneity and uniformity

mentions of the term "homo" related to various contexts of society and biology

No Comments

No Known Activations