INDEX

Explanations

mentions of specific holidays or specific dates

oai_token-act-pair · gpt-3.5-turbo

references to various holidays and commemorative days

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

oxin

-0.79

itic

-0.76

urally

-0.72

izabeth

-0.72

ioch

-0.71

oidal

-0.69

 Argon

-0.68

URES

-0.68

oad

-0.67

OSED

-0.66

POSITIVE LOGITS

 Parade

1.31

 Weekend

1.22

 Massacre

1.21

 celebrations

1.18

 weekend

1.14

 festivities

1.14

1.06

dream

1.03

 Celebration

1.02

0.99

Activations Density 0.062%

mentions of specific holidays or specific dates

references to various holidays and commemorative days

No Comments

No Known Activations