INDEX

Explanations

phrases related to 'Our'

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude and acknowledgment of relationships

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

conom

-0.79

puff

-0.77

hift

-0.67

cum

-0.67

edi

-0.65

ppings

-0.65

icter

-0.65

Ø³

-0.64

 akin

-0.64

arth

-0.63

POSITIVE LOGITS

selves

1.34

own

0.96

 hearts

0.96

 beloved

0.92

 heroine

0.89

 selves

0.88

 asses

0.87

 dear

0.86

 fearless

0.85

 esteemed

0.84

Activations Density 0.149%

phrases related to 'Our'

expressions of gratitude and acknowledgment of relationships

No Comments

No Known Activations