INDEX

Explanations

terms related to businesses and organizations that are family-owned or family-friendly

oai_token-act-pair · gpt-3.5-turbo

concepts related to family structures and family-oriented themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

hole

-0.72

iov

-0.70

umatic

-0.69

hol

-0.68

shit

-0.68

wagen

-0.66

issan

-0.65

ovsky

-0.65

henko

-0.63

claw

-0.63

POSITIVE LOGITS

 belongings

0.72

 caregivers

0.71

 kindred

0.70

 elders

0.67

 Weston

0.67

 mourning

0.66

 holiday

0.65

 reunion

0.65

 bond

0.65

 ravaged

0.65

Activations Density 0.271%

terms related to businesses and organizations that are family-owned or family-friendly

concepts related to family structures and family-oriented themes

No Comments

No Known Activations