INDEX

Explanations

technology-related terms and concepts, especially those related to encryption, permissions, and manufacturing

oai_token-act-pair · gpt-3.5-turbo

references to technology and related companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Seym

-0.66

ournal

-0.61

yss

-0.61

ocide

-0.60

ACP

-0.60

Ø¯

-0.60

chens

-0.59

utenberg

-0.59

 contrace

-0.59

 horizont

-0.57

POSITIVE LOGITS

 Lenovo

0.71

 NVIDIA

0.70

 Nvidia

0.64

 Robot

0.64

 ASUS

0.63

 Silicon

0.61

itial

0.61

 Asus

0.61

 Konami

0.60

OEM

0.60

Activations Density 1.700%

technology-related terms and concepts, especially those related to encryption, permissions, and manufacturing

references to technology and related companies

No Comments

No Known Activations