INDEX

Explanations

phrases describing social interactions and relationships

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation usage, particularly commas

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

¬¼

-0.67

izen

-0.65

oÄŁan

-0.62

reprene

-0.62

ģĸ

-0.61

enary

-0.60

reated

-0.60

uber

-0.59

ocl

-0.59

utive

-0.58

POSITIVE LOGITS

 though

1.10

 albeit

1.01

but

0.99

 however

0.99

 although

0.99

 including

0.90

 meanwhile

0.89

 especially

0.87

 whereas

0.84

huh

0.76

Activations Density 0.605%

phrases describing social interactions and relationships

instances of punctuation usage, particularly commas

No Comments

No Known Activations