INDEX

Explanations

phrases introducing additional information or contrasting ideas

oai_token-act-pair · gpt-3.5-turbo

phrases indicating comparison or additional information

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

body

-0.80

ruction

-0.76

ona

-0.74

 guiActiveUnfocused

-0.71

´

-0.70

anmar

-0.69

opter

-0.69

owe

-0.69

igmatic

-0.68

taboola

-0.68

POSITIVE LOGITS

 besides

0.74

 moreover

0.73

 THERE

0.67

 though

0.66

 despite

0.65

 Mehran

0.63

 secondly

0.63

 unlike

0.62

 Kejriwal

0.62

 there

0.62

Activations Density 0.157%

phrases introducing additional information or contrasting ideas

phrases indicating comparison or additional information

No Comments

No Known Activations