INDEX

Explanations

terms related to security measures and technologies

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 @ 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

————————

-0.74

hops

-0.74

VL

-0.73

how

-0.70

hoff

-0.69

INA

-0.68

thus

-0.67

è¦ļéĨĴ

-0.67

_>

-0.67

bid

-0.66

POSITIVE LOGITS

 secure

0.93

 cryptographic

0.91

 Secure

0.81

ably

0.78

 adolesc

0.77

 enclave

0.77

 handshake

0.74

 connections

0.74

 perimeter

0.73

 cryptography

0.72

Activations Density 0.011%

terms related to security measures and technologies

terms related to security

No Comments

No Known Activations