INDEX

Explanations

mentions of new developments or updates

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "New."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

uddin

-0.74

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.71

ascript

-0.66

odox

-0.65

xual

-0.64

``

-0.64

 actionGroup

-0.64

ppe

-0.63

ÃĥÃĤ

-0.63

agn

-0.62

POSITIVE LOGITS

 Zealand

1.20

 York

1.17

foundland

1.12

bies

1.12

 Orleans

1.06

bie

1.04

 Hampshire

1.00

 YORK

0.97

York

0.96

 Yorker

0.95

Activations Density 0.062%

mentions of new developments or updates

occurrences of the word "New."

No Comments

No Known Activations