INDEX

Explanations

phrases related to cybersecurity software, particularly Kaspersky Lab

oai_token-act-pair · gpt-3.5-turbo

references to a specific lab or organization involved in technology and espionage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

glers

-0.91

liam

-0.88

externalActionCode

-0.79

soDeliveryDate

-0.74

onen

-0.70

falls

-0.66

abul

-0.66

udeb

-0.65

shr

-0.65

allo

-0.65

POSITIVE LOGITS

 Universe

0.78

Gate

0.77

 Bros

0.76

Flight

0.76

 Gate

0.74

 Springs

0.69

 Rising

0.68

 Horowitz

0.67

 Islands

0.66

 Valley

0.66

Activations Density 0.230%

phrases related to cybersecurity software, particularly Kaspersky Lab

references to a specific lab or organization involved in technology and espionage

No Comments

No Known Activations