INDEX

Explanations

words related to social media posts and interactions

oai_token-act-pair · gpt-3.5-turbo

references to social media interactions and public discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

OV

-0.68

OUS

-0.64

asus

-0.64

 Design

-0.64

 Sabha

-0.63

ded

-0.63

ESA

-0.61

scape

-0.61

 Libre

-0.61

ress

-0.60

POSITIVE LOGITS

uggest

1.49

mith

1.47

poons

1.37

ettings

1.32

pring

1.27

hip

1.26

hips

1.21

uits

1.16

hops

1.14

cape

1.12

Activations Density 0.189%

words related to social media posts and interactions

references to social media interactions and public discourse

No Comments

No Known Activations