INDEX

Explanations

words related to technology, communication, and events

oai_token-act-pair · gpt-3.5-turbo

variations of the word "en."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 hitch

-0.65

mson

-0.63

enhagen

-0.62

 unrecogn

-0.61

 Nicarag

-0.60

 Canaveral

-0.59

 compan

-0.59

milo

-0.58

 shake

-0.57

 aborted

-0.56

POSITIVE LOGITS

heimer

1.28

esis

1.19

bach

1.18

baum

1.16

wald

1.11

berger

1.10

ews

1.09

heim

1.09

auts

1.09

zyme

1.06

Activations Density 0.075%

words related to technology, communication, and events

variations of the word "en."

No Comments

No Known Activations