INDEX

Explanations

technical terms and references

oai_token-act-pair · gpt-3.5-turbo

references to movies, films, and relevant media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

actionDate

-0.66

 periodic

-0.61

Joined

-0.60

soDeliveryDate

-0.59

locked

-0.58

 customary

-0.56

ãĥĥãĤ¯

-0.55

 Canaveral

-0.55

una

-0.54

ARA

-0.53

POSITIVE LOGITS

 proves

1.31

 provides

1.30

 shines

1.29

 reminds

1.27

 delivers

1.27

 embodies

1.25

 offers

1.23

 brings

1.21

 solves

1.21

 demonstrates

1.20

Activations Density 0.642%

technical terms and references

references to movies, films, and relevant media

No Comments

No Known Activations