INDEX

Explanations

mentions or references to organizations or institutions

oai_token-act-pair · gpt-3.5-turbo

mentions of specific brands or organizations, particularly in a tech context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ©

-0.67

ãĥĥãĥĪ

-0.65

 Schne

-0.63

ozyg

-0.61

ogue

-0.61

 MacArthur

-0.59

mer

-0.59

 Maxwell

-0.58

ows

-0.58

endor

-0.58

POSITIVE LOGITS

daq

1.03

ADA

1.03

leep

1.02

bestos

1.00

ENA

1.00

ynchronous

0.99

TER

0.99

ylum

0.98

ync

0.97

ILE

0.97

Activations Density 0.018%

mentions or references to organizations or institutions

mentions of specific brands or organizations, particularly in a tech context

No Comments

No Known Activations