INDEX

Explanations

keywords related to security and encryption

oai_token-act-pair · gpt-3.5-turbo

terms related to security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

swick

-0.79

bender

-0.75

hops

-0.75

leton

-0.72

Â¢

-0.69

è¦ļéĨĴ

-0.69

skill

-0.68

oths

-0.68

irez

-0.67

VL

-0.67

POSITIVE LOGITS

 cryptographic

0.86

 enclave

0.85

 handshake

0.82

 perimeter

0.78

 secure

0.78

 Secure

0.75

 space

0.72

heed

0.72

 satell

0.71

 communication

0.70

Activations Density 0.016%

keywords related to security and encryption

terms related to security

No Comments

No Known Activations