INDEX

Explanations

words related to actions and activities

oai_token-act-pair · gpt-3.5-turbo

various forms of social interactions and transactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Registered

-0.68

asus

-0.66

 skelet

-0.60

Connector

-0.58

 Refuge

-0.58

ishly

-0.57

 founding

-0.56

scape

-0.56

 reservoir

-0.56

 bikini

-0.55

POSITIVE LOGITS

creen

1.43

paces

1.32

hips

1.25

peed

1.19

heet

1.17

pring

1.17

ettings

1.14

ync

1.13

hots

1.12

hift

1.11

Activations Density 0.560%

words related to actions and activities

various forms of social interactions and transactions

No Comments

No Known Activations