INDEX

Explanations

words related to names and surnames

oai_token-act-pair · gpt-3.5-turbo

proper nouns or names associated with notable figures or entities

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

taboola

-0.85

 lapt

-0.67

 pestic

-0.65

ciating

-0.64

 feder

-0.63

pse

-0.62

 contrace

-0.61

 satell

-0.61

 pregn

-0.61

 rall

-0.60

POSITIVE LOGITS

inki

1.18

lich

1.00

kamp

1.00

schild

0.98

mann

0.97

feld

0.87

beck

0.86

angs

0.83

stad

0.83

igans

0.82

Activations Density 0.254%

words related to names and surnames

proper nouns or names associated with notable figures or entities

No Comments

No Known Activations