INDEX

Explanations

terms related to actions or verbs ending in 'ing'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 's'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hyde

-0.69

 Wikileaks

-0.69

 Pharaoh

-0.65

tainment

-0.64

 unrestricted

-0.63

RIP

-0.62

 undecided

-0.62

 starters

-0.60

 Sacrament

-0.60

NAS

-0.60

POSITIVE LOGITS

outher

1.31

ixties

1.24

uss

1.22

igm

1.21

esame

1.21

ierra

1.20

ifting

1.20

igma

1.18

iren

1.18

idd

1.17

Activations Density 0.023%

terms related to actions or verbs ending in 'ing'

occurrences of the letter 's'

No Comments

No Known Activations