INDEX

Explanations

phrases related to personal interactions and conflicts

oai_token-act-pair · gpt-3.5-turbo

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

ossus

-0.77

 cures

-0.75

 prest

-0.73

 staggered

-0.72

 Keynes

-0.72

 doomed

-0.71

 unbeat

-0.71

 unbeaten

-0.71

 reinvent

-0.70

 marvel

-0.70

POSITIVE LOGITS

 âĢ

1.22

âĢ

1.17

 hijab

1.07

 pronouns

1.01

ã

0.94

[+

0.93

 GamerGate

0.93

 harassment

0.91

 disrespectful

0.90

 offended

0.86

Activations Density 0.868%

phrases related to personal interactions and conflicts

No Comments

No Known Activations