INDEX

Explanations

words related to agreements or plans between parties

oai_token-act-pair · gpt-3.5-turbo

words associated with organizational structures or configurations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

clamation

-0.80

tro

-0.72

âĵĺ

-0.70

 thirsty

-0.69

CVE

-0.68

azed

-0.66

burning

-0.62

ãĥ©ãĥ³

-0.62

inas

-0.61

gur

-0.61

POSITIVE LOGITS

 arrangements

1.24

 arrang

1.19

 arrangement

1.16

owship

0.75

 Seym

0.75

 arranging

0.74

eering

0.73

 arranged

0.73

ally

0.72

ttes

0.72

Activations Density 0.012%

words related to agreements or plans between parties

words associated with organizational structures or configurations

No Comments

No Known Activations