INDEX

Explanations

URLs or references

oai_token-act-pair · gpt-3.5-turbo

words or phrases that relate to the act of eating or food-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

etheless

-0.75

icum

-0.75

igans

-0.70

inatory

-0.67

acles

-0.66

hips

-0.64

ization

-0.63

-0.62

aries

-0.61

odd

-0.60

POSITIVE LOGITS

lli

1.52

llan

1.44

xual

1.42

lla

1.34

ll

1.34

lled

1.34

vich

1.30

Ã±o

1.29

llo

1.27

chnology

1.25

Activations Density 0.289%

URLs or references

words or phrases that relate to the act of eating or food-related concepts

No Comments

No Known Activations