INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

names and terms associated with specific individuals or characters

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

ivity

-0.75

verted

-0.68

encia

-0.68

ĪĴ

-0.65

 microwave

-0.63

×Ļ×

-0.63

ivism

-0.62

mond

-0.62

ional

-0.62

 MacArthur

-0.61

POSITIVE LOGITS

emonic

0.79

astern

0.76

useum

0.74

ixture

0.72

hattan

0.71

uppet

0.70

nih

0.68

pas

0.68

ongo

0.67

achine

0.67

Activations Density 0.151%

names of individuals

names and terms associated with specific individuals or characters

No Comments

No Known Activations