INDEX

Explanations

terms related to size or scale, particularly in the context of large or significant quantities

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 counsel

-0.67

gently

-0.64

 carbohyd

-0.64

mates

-0.62

 Constable

-0.62

ruciating

-0.61

ryu

-0.59

xit

-0.59

 Elise

-0.57

 Jinn

-0.57

POSITIVE LOGITS

(>

1.05

 conglomer

0.86

emouth

0.72

 congr

0.71

 chunk

0.71

 multinational

0.70

 empires

0.69

 deficits

0.68

 iceberg

0.68

bucks

0.67

Activations Density 0.502%

terms related to size or scale, particularly in the context of large or significant quantities

No Comments

No Known Activations