INDEX

Explanations

words related to revision, changes, or modifications in a given context

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of "re-" which indicates repetition, reopening, rethinking, or redoing something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Phar

-0.70

 negotiator

-0.70

 Institution

-0.65

eteria

-0.64

 Sturgeon

-0.64

 negotiators

-0.63

DragonMagazine

-0.63

 Everywhere

-0.62

NESS

-0.62

 Pebble

-0.62

POSITIVE LOGITS

clamation

1.16

becca

1.14

ordered

1.11

authorized

1.07

ordering

1.05

charging

1.05

interpret

1.03

fect

1.02

apers

1.02

prise

1.02

Activations Density 0.024%

words related to revision, changes, or modifications in a given context

words related to the concept of "re-" which indicates repetition, reopening, rethinking, or redoing something

No Comments

No Known Activations