INDEX

Explanations

loading indicators

oai_token-act-pair · gpt-3.5-turbo

instances of loading messages or similar indicators of process activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 perspect

-0.83

 spoof

-0.75

 exile

-0.69

 welf

-0.68

 sided

-0.68

 strengths

-0.67

 livest

-0.66

 exiled

-0.64

 sabot

-0.63

 polymorph

-0.63

POSITIVE LOGITS

 Related

1.13

 Loading

1.02

Comments

0.91

<|endoftext|>

0.91

 Flavoring

0.86

 Previous

0.81

*/

0.76

 Contents

0.72

Related

0.71

 Submit

0.70

Activations Density 0.012%

loading indicators

instances of loading messages or similar indicators of process activity

No Comments

No Known Activations