INDEX

Explanations

full stops at the end of sentences

oai_token-act-pair · gpt-3.5-turbo

sentences that indicate a conclusion or finality

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

 disemb

-0.80

 haul

-0.80

 defe

-0.76

 disarm

-0.76

 quir

-0.75

 brist

-0.75

¥ŀ

-0.71

 landfall

-0.69

 bounded

-0.68

 glim

-0.67

POSITIVE LOGITS

 Lastly

1.86

 Whilst

1.55

 Needless

1.55

 Luckily

1.54

 Therefore

1.53

 Thankfully

1.53

 Additionally

1.52

 Unfortunately

1.51

 Regardless

1.51

 Furthermore

1.50

Activations Density 0.547%

full stops at the end of sentences

sentences that indicate a conclusion or finality

No Comments

No Known Activations