INDEX

Explanations

references to specific numbered items or entities within a list

oai_token-act-pair · gpt-3.5-turbo

special character patterns or formatting elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Pioneer

-0.80

 Cran

-0.65

 courier

-0.65

 Paradise

-0.64

 Patrol

-0.62

iens

-0.61

 seller

-0.60

 Polar

-0.59

 Anglo

-0.59

 Evangel

-0.58

POSITIVE LOGITS

###

4.48

####

2.77

##

2.64

###

2.36

########

2.24

################

1.92

##

1.72

################################

1.60

 #####

1.55

1.37

Activations Density 0.033%

references to specific numbered items or entities within a list

special character patterns or formatting elements

No Comments

No Known Activations