INDEX

Explanations

phrases related to positive attributes or accomplishments

oai_token-act-pair · gpt-3.5-turbo

phrases indicating emotions and human experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

)]

-0.54

],

-0.50

 Description

-0.50

Opp

-0.49

 Mons

-0.48

 Originally

-0.48

 Dimensions

-0.48

?",

-0.48

inventoryQuantity

-0.48

 Burke

-0.48

POSITIVE LOGITS

 accordingly

1.07

 thereafter

0.88

 thereof

0.75

 afterward

0.72

 afterwards

0.68

 therein

0.68

 attRot

0.61

 wherever

0.59

 thereto

0.58

 versa

0.57

Activations Density 2.365%

phrases related to positive attributes or accomplishments

phrases indicating emotions and human experiences

No Comments

No Known Activations