INDEX

Explanations

abbreviations related to organizations or titles with capitalized letters

oai_token-act-pair · gpt-3.5-turbo

instances of text that do not contain any words, specifically empty text segments

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

assetsadobe

-0.86

Bam

-0.68

 Marketable

-0.65

Lov

-0.64

gra

-0.64

 ende

-0.62

wid

-0.61

 Wast

-0.61

cle

-0.60

kh

-0.60

POSITIVE LOGITS

PD

1.06

MC

1.02

PM

1.01

FP

1.00

BM

1.00

AMA

1.00

PC

0.99

IP

0.99

GC

0.99

FC

0.98

Activations Density 0.224%

abbreviations related to organizations or titles with capitalized letters

instances of text that do not contain any words, specifically empty text segments

No Comments

No Known Activations