INDEX

Explanations

descriptions or mentions of gifts

oai_token-act-pair · gpt-3.5-turbo

terms related to gifts and gift-giving

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

idents

-0.73

tics

-0.72

Gas

-0.69

 Occupations

-0.67

ane

-0.67

utsu

-0.66

ANE

-0.66

anned

-0.64

arios

-0.63

POSITIVE LOGITS

giving

1.17

 gift

1.00

 baskets

0.96

 gifts

0.96

 recipient

0.94

 basket

0.91

 bestowed

0.89

 recipients

0.88

 Gift

0.82

wra

0.80

Activations Density 0.043%

descriptions or mentions of gifts

terms related to gifts and gift-giving

No Comments

No Known Activations