INDEX

Explanations

occurrences related to gifting, receiving, and giving

oai_token-act-pair · gpt-3.5-turbo

references to gifts and gifting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

older

-0.63

pse

-0.63

Dick

-0.62

 Silent

-0.59

 unregulated

-0.59

 solitary

-0.58

 Ibid

-0.58

itch

-0.58

 constitu

-0.58

average

-0.57

POSITIVE LOGITS

 gift

1.27

 gifts

1.24

 Gifts

1.07

 Gift

1.07

 baskets

0.96

giving

0.95

FontSize

0.82

abilia

0.82

apult

0.81

nels

0.80

Activations Density 0.010%

occurrences related to gifting, receiving, and giving

references to gifts and gifting

No Comments

No Known Activations