INDEX

Explanations

phrases related to specific locations or organizations

oai_token-act-pair · gpt-3.5-turbo

references to specific intelligence agencies and their operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 entitlement

-0.69

 concess

-0.67

 Explicit

-0.64

Qi

-0.64

 Weiner

-0.63

Wu

-0.62

Coh

-0.61

 Kindle

-0.61

BU

-0.61

ensing

-0.60

POSITIVE LOGITS

raltar

1.07

CHQ

1.06

racuse

1.00

anooga

0.97

emouth

0.94

mingham

0.85

DragonMagazine

0.80

alion

0.79

mpeg

0.76

OPS

0.75

Activations Density 0.030%

phrases related to specific locations or organizations

references to specific intelligence agencies and their operations

No Comments

No Known Activations