INDEX

Explanations

mentions of the Transportation Security Administration (TSA)

oai_token-act-pair · gpt-3.5-turbo

references to the Transportation Security Administration (TSA) and related security measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

theless

-0.99

hips

-0.75

orthern

-0.74

taboola

-0.72

 Lazarus

-0.71

-0.67

 Celt

-0.67

ÑĮ

-0.67

pring

-0.66

é¾įå

-0.64

POSITIVE LOGITS

TSA

0.97

 checkpoints

0.85

 checkpoint

0.83

 brass

0.77

 bureaucracy

0.72

OSH

0.71

 clearance

0.70

 screening

0.67

senal

0.67

istani

0.66

Activations Density 0.013%

mentions of the Transportation Security Administration (TSA)

references to the Transportation Security Administration (TSA) and related security measures

No Comments

No Known Activations