INDEX

Explanations

words containing the substring "hom."

oai_token-act-pair · gpt-3.5-turbo

references to homogeneity in groups or populations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FUL

-0.82

CLASSIFIED

-0.79

UGE

-0.78

 canopy

-0.75

FORE

-0.72

Accessory

-0.71

ESSION

-0.68

 Grip

-0.67

REE

-0.67

OUP

-0.67

POSITIVE LOGITS

onym

1.32

estead

1.31

ogenous

1.31

ogeneous

1.26

ogeneity

1.25

icidal

1.12

ozyg

1.11

oph

1.07

onymous

1.06

onyms

1.03

Activations Density 0.013%

words containing the substring "hom."

references to homogeneity in groups or populations

No Comments

No Known Activations