INDEX

Explanations

mentions of "our" or possessive forms in a text

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

puff

-0.78

tar

-0.77

bender

-0.77

icter

-0.75

atican

-0.70

conom

-0.68

 REUTERS

-0.68

more

-0.68

netflix

-0.67

 contradicts

-0.66

POSITIVE LOGITS

selves

1.47

own

1.22

 respective

0.98

 collective

0.97

 selves

0.94

 asses

0.93

 adversaries

0.90

 dear

0.90

 motto

0.86

 beloved

0.84

Activations Density 0.123%

mentions of "our" or possessive forms in a text

expressions of gratitude and appreciation

No Comments

No Known Activations